The fact that so many people fear loss of income as a result of better AI is a real indictment of our economic system. A better system that more fairly distributed economic productivity would make people welcome better AI because they could be confident it would make everyone wealthier instead of just a few people rich enough to be Goa'uld.
I don’t know what country you live in, but I can tell you how it is in Sweden. As a freelancer I pay appropriately 70% of what I charge in taxes. How high do you think taxes can get before people stop putting energy into raising their productivity?
Better distribution is through capital tax, not income tax. Taxing workers even more is the opposite of sharing productivity gains captured by shareholders. Are capital gains and dividends taxed at least at 70% in Sweden?
1. Salary is your company's money that becomes your money.
2. Capital tax is tax on your company's money.
3. Income tax is tax on your money.
With either tax, the economic system that consists of you and your employer is being robbed.
Speaking of which, if someone takes your groceries and runs, just before you have paid for them, that is shoplifting. If it's just after you paid, it's robbery. You might think you're better off with the former, but shoplifting raises prices; some of it is shifted onto you, so that it is effectively robbery.
1. Companies only have money because of the work I and others do.
2. It doesn't follow that when companies have more money their workers get more. Evidence is: record profits concomitant with layoffs, corporate profits vs wages, etc etc.
3. Taxes fund a government that answers to me. Capital powers corporations that not only don't answer to me but likely want to exploit me.
If what you were saying were true, there would be no corporate tax, and probably no worker protections, no social safety net, no building safety standards, no regulatory apparatus, no antitrust, etc etc.
I like that stuff, and I'm pretty confident corporations wouldn't have done it themselves without a democratic government forcing them to.
There's a meaningful difference between democratic governments and corporations, and governments don't have to be perfect for this to be true.
The situation is trickle down from laissez-faire is definitely proven wrong just by the situation we are in and is the starting point of the discussion. Tax is just a tool to correct the failure of the system of failing to correctly redistribute productivity gains from workers starting a few decades ago (and the point above is with the promises of LLM it’s crucial we address that situation). Robbery or not is not the debate here, income tax higher than capital tax is just a good candidate cause and solution (given historical data), but of course we can discuss alternatives.
>With either tax, the economic system that consists of you and your employer is being robbed
Except differences in tax rates will have significant impact on what type of income people want to earn. If personal income is taxed lower than capital, then people will want to increase their income through work.
If personal income is taxed higher than capital, people are incentivized to build more machines than the economy needs and this will put people out of work.
by tax revenues
In China, corporations pay more than 2 times more taxes than individuals (in the US, individuals pay almost 6 times more taxes than corporations).
China: corporate income tax (19%), individual income tax (7%)
USA: corporate income tax (7.6%), individual income tax (41.1%)
IMHO that is very misleading in this context where there are a lot of Americans.
If the VAT rates went to 0% you would still get to keep the exact same amount as with the current 25% rate. And when discussing B2B prices VAT is never included, as it is generally not an expense for the company but rather just an accounting detail.
I would include VAT. No matter B2B or not, it's how much your end customer pays is what matters. Yes, business will pass on this tax further, but end consumer won't be able to claim it. It's the same as a sales tax in the US. To include it in price or not is more a psychological thing (in the US it's not included in price). When I pay $106.25 for something it makes a little difference for me that $6.25 goes to my state or passed to the previous business, and if I only have $100 you lost me. That's the reality.
Basically it's very similar to debates about US taxes. Sure, it's not 70%, but things add up quickly. Income tax, social security, medicare, medical insurance, sales tax. The usual argument is "but, but ... it's not me who is paying my medical insurance or half of social taxes, it's my employer, so it's not my tax". Well, it is. That's the money your employer would have paid _you_ if those taxes hadn't existed.
Not to mention, things that fall outside of capital / income taxes which increase the overall percentage in sneaky ways in the US: car registration fees, the death tax, property taxes, student loan repayments (depending on your view of subsidized university).
We can actually be certain that humans work the other way since we ran huge experiments in labs called the Soviet Union and China. In those experiments we found out that people worked way less/not at all when there was no economic incentive to do so.
Sure that’s risky for 100% of population. But for 0.1 percent of population who makes many millions a year, who cares? No one is that special of a snowflake we need to optimize for their productivity. Most of those people are either already workaholics or already retired on a yatch.
Societies taxing their entrepreneurs at 10 and at 90% are always vastly different. This difference in turn heavily influences every participant’s system of motivations, so comparing these two numbers alone is usually not very helpful
That’s not true. Many companies people work at provide them little to no incentive to work harder or better, yet still a lot of people try to do so. Lots of places have almost no possibility of promotion just the ability to go elsewhere. Some professions like teaching, nursing pharmacy treat all workers as interchangeable with no performance incentives.
I can tell you that there is no way I’d be doing what I do if it wasn’t for the money. I’d be developing useless keyboard firmware or some other junk no one but me would care about. It would provide minimal value to the world.
Who pays nurses more just because they are good? In a lot of professions rates are set by governments or institutions and there is not enough competition between businesses for wages.
Any private clinic would pay the better nurse more? You can check this quickly on job-listing portals – nurse wages are in the 20000-100000k/year range, so clearly supply and demand as well as qualification are determining it. Which socialist country is it where wages are ceiled by the government?
Agreed. After all, that is the equivalent rate for all work done in the commons, on free software for example. Zero dollars earned, but somehow the incentive is still there. Money is not the only thing that motivates human beings.
Sure this works for creative endeavors. Now what would motivate someone to pick fruit in the summer Sun? Or clean toilets in a corporate office?
Sure you could say, "there are some people who just enjoy picking fruit." But are there enough people to satisfy the demand? And even if there are, what do you do with them as that demand decreases? The people who love picking fruit will have to clean toilets.
I believe this is why the income tax is so popular with economists. Other taxes create some type of negative feedback where raising the tax decreases transactions and shifts capital elsewhere. But with the income tax people have no choice but to keep working and may even have to work more. So the "economy" benefits because more labor/capital can be squeezed out of individuals without slowing anything down.
I wonder why people endlessly argue how much they should tax the rich and the poor, there is only one answer: 100% of everything, i.e wealth, income, gifts etc. It's a nice round number and everybody is taxed fairly.
Interesting, my understanding is exactly the opposite. In my opinion the reason why so many people don’t care much (or are so in love with admin jobs) in Sweden is precisely because it’s too safe?
The Nordic countries are actually the easiest place in the world to earn at least 30 million dollars (or become billionaire for that case) exactly because of the welfare system: https://youtu.be/A9UmdY0E8hU
When you don’t have to struggle for a living, you’re more free to take risks and start your own business. Workers accept disruptive innovation and being let go, knowing that the state will help them reskill if necessary.
Edit: Changed sentence from "earn a million dollars" to "30 million dollars" to reflect the actual video contents. (Mea culpa.)
USA demolishing most everyone else, as you'd expect if you own what you create. Almost 10% of 400 million people are millionaires in the USA! Insanely productive all things considered.
Also kind of shockingly the USA has the most progressive tax system, I believe -- the vast majority of those paying are high earners, low earners pay barely any taxes and can save a lot.
People in the USA who want to have a European-style welfare state don't realize that American high-earners already pay European levels of tax. The American lower and middle classes pay a lot less of their incomes - that would be the group that would have to pay for an American welfare state. That won't go over well...
Having a single payer healthcare system would increase taxes but could decrease overall costs by 50% (since US pays 2x what other equivalent countries pay).
Beyond that, we have an issue where corporations and high-net worth individuals aren’t paying taxes, which could prevent onerous taxes on the middle class. No nation really taxes the rich (cf. the Panama Papers).
We are talking past each other: I'm saying there are lots of ways that the wealthy avoid taxes, such as borrowing against equities for expenses (https://www.wsj.com/articles/buy-borrow-die-how-rich-america...). Trump had a private jet but paid $750.00 in income tax for a couple of years. Additionally, capital gains taxes are lower than many income brackets (cf. Buffet's famous quote about being taxed more than his assistant). Finally, carried interest loophole allows private equity managers to classify services as capital gains.
Basically, if you have enough equity, a bank will loan you the money you need, while you can leave those stocks untouched. You don't have to pay any tax, let alone the extremely preferential capital gains tax.
US has a tax gap of perhaps $1 trillion, and much of that is wealthy Americans who are too hard to pursue: https://www.nytimes.com/2021/04/13/business/irs-tax-gap.html. That could be 50% of the bill if we were able to cut healthcare expenses by dropping insurance companies, removing pharma control of prices, etc., to try to attain similar OECD healthcare costs.
The US is in a unique situation. We have to both reduce the amount of rent-seekers within the healthcare system while increasing the taxes we levy on the wealthy. Universal care might mean an increase in taxes on the middle-class, but universal care will ultimately reduce their expenses since it's more efficient.
PS. Please don't attack people personally: it's much better to say, "This comment does not account for X," than "You seem very uniformed [sic]?"
PPS. If you need a poignant example of the failure of the US healthcare system, look no further than maternal mortality rates. What a disgrace.
It's not necessary about amount, but about distribution. Let's say a medical tax in Germany is 14.6% (correct me if I'm wrong), my medical insurance here in the US for a family of 2 is around 14% (yes, it's paid by my employer, but there is no free lunch and I consider it _my_ tax). The only problem here is that payment is fixed, so if I had 50% of what I have now (and that would be a median salary in my state) it would be 28%. Also if I lose my job I will have to pay it in full myself, from after-tax money. Unlike Germany. Oops. So I'm already paying on par with Germany (when I'm employed), and I would pay twice, of even triple of that if I was an average worker.
The tax rate in Germany is 42% on income over 62000 euros. That covers everything, but doesn't include any local or municipal taxes. The VAT is 19% on top of that.
In other words, a 42% federal income tax plus (roughly) a 20% federal sales tax.
You are conveniently leaving out payroll taxes which constitute another ~35%. So 42% becomes ~77%. 19% doesn't technically apply to the payroll, but it does apply when you buy something.
The maximum payroll tax is 42% for incomes above 62k Euros. The part of income below has a tax excempt amount of ~10k, then a linear progressive tax. (There is an rate of 45% for incomes over 250k, but let’s skip that for the argument.)
There are also some tax reducing things, but let’s say you have a taxable gross income in the range of 60k. The deductions are as follows:
- 25% payroll tax (which is the tax _average_, only the amount above 62k is taxed with 42%)
- 7.3% healthcare (or 14.6% if you are self-employed)
- some percentage for other public insurances
Gives you around 65% net income, from which you pay 19% VAT for most things you buy as consumer. But e.g. rent doesn’t have a VAT.
If your income is higher (as I wrote in my other comment), the healthcare / public insurance cost is capped, so every Euro above 62k is taxed with 42 (or 45) percent. If your income is lower you simply pay less taxes (relatively) and might have 80% or more net income.
Yep, but you need to count employer paid taxes too to get the whole picture. Tax base will be different (+ 7.3% healthcare + 9.3% pension + 1.5% unemployment), so if your base is ~1.17 of your "official" base, the effective tax becomes (0.35 + 0.17) / 1.17 = 45% (leaving you with 55%). Which is in line with the chart I posted.
Now here's how it works in the US. Let's take my $170K household income (it's 2x of state median in Massachusetts, but 1x in my town). My effective tax rate (without medical insurance and without employer part of payroll taxes) is 33%, but with employer taxes and after tax base adjustment it's going to be (0.33 + 0.08) / 1.08 = 38% (I'm ignoring social security cap here, but it won't make a big difference). But we left out a very important part, and it's medical insurance. Let's add 24K/year (14%) to the mix, then it becomes (0.33 + 0.08 + 0.14) / 1.22 = 45%. Oops! Sounds like I'm paying the same percentage as in Germany. Sure, I have 2x of median, but for 1x things are getting even more ugly, because 24K will stay the same, and while the income tax is lower, medical will take its part and more.
Of course I still bring home more than an average German family, yet expenses are different too so it's hard to compare. Sure, I can buy more junk, and I have a bigger home so I still have some place to live after I placed all that junk :) But to the original comment:
> The American lower and middle classes pay a lot less of their incomes - that would be the group that would have to pay for an American welfare state. That won't go over well...
No, American lower and middle class doesn't pay "a lot less of their incomes", it's simply not true.
Now do the VAT. Almost everyone who does the math on this (counting healthcare as a tax in the US) finds that only considering the income portion of your taxes, it's about equal. In most places in Europe, you also have the VAT acting as an extra tax. Your tax burden would be a lot higher.
Also, you must be thinking of your marginal rate being 33% - your federal taxes should be under 20% of your income at $170k, even if filing as single. In Germany, your tax rate would be about 27%.
Agree on VAT, but MA also has 6.25% sales tax which I didn't consider, that is if you want to start from revenue. So the difference will be less than 19%. Also VAT in Germany is not 19% on everything, there are exemptions and low rate of 7%.
33% is not a marginal rate, it's an effective tax rate (filing jointly) including payroll taxes which are deducted from my wages, I mentioned it. Also we have a state tax in MA which is also included in 33%.
In any case there are other taxes too (e.g. gas excise, vehicle excise, property tax etc.), so I'm not trying to compare the whole tax burden, that would be too much for HN. But regarding payroll taxes -- they are pretty close even if you consider VAT, certainly not a "lot less", it's a myth propagated by politicians. So the question is: we pay (almost) "welfare state" taxes, where is my part of a welfare state?
Yeah, you live in a high-tax state - counting that and payroll tax would make it to 33%. However, you can deduct a good fraction of that tax (actually all of it) from your federal taxes. Also, you included the cost of your healthcare in your calculation, so you are getting "welfare state" benefits for that cost. As to your taxes, those are paying for a welfare state for people who are less well off than you. I'm pretty sure you are in the 90th percentile on income, by the way, so you're not actually in the lower class, and arguably not even the middle class (although that level of income in a rich state like MA feels middle class).
All those other taxes exist in Germany too, by the way, and are much higher.
MA is not a "high-tax state", it's in the middle by an overall tax burden (depending how you count), so it's another myth. Check this for example: https://wallethub.com/edu/states-with-highest-lowest-tax-bur.... Also I'm not in the top 10% percentile, more like in the top 20% in MA. Give me your definition of the "middle class". Also I explained that for the "lower class" medical payments are even higher.
No, I'm not getting "welfare state" benefits, I'm getting a pretty crappy medical service for a price which is waaay higher than in Germany. And if I lose my job I will be paying 2K/month + copays and co-insurances, not mentioning deductibles, unlike in Germany. And God forbids you get into a hospital without insurance, your jaw will drop to the floor when you see the bill.
Have you ever been in the Boston subway? Compare it with almost any city in Europe, hell, even with Montreal. Tell me which welfare state has subways like Boston or NYC? Commuter rail like in Boston? NYC commuter rail is a bit better, but still is not even close to German railways.
And all of the above we get for taxes which are very similar to Germany. No, they are not much lower, it's something with your math. And in absolute value we pay waaay more than in Germany given higher salaries.
Here's some comparison, but it is misleading when it comes to the US. Technically medical insurance (de facto mandatory) can be from ~15% to >25%, depending on the income. It's not reflected on the picture, so in reality tax burden in the US might even be more than in Belgium (VAT aside).
https://upload.wikimedia.org/wikipedia/commons/4/49/Payroll_...
The public healthcare rate is indeed 14.6% but half of that is paid by your employer. Of course in the end it doesn’t matter, just that only 7.3% from your gross income will be reduced (also there are rates for nursing care insurance, pension insurance, unemployment insurance – a middle-class income pays 35–50% for tax and insurance).
Public healthcare is obligatory for all employees except you’re earning more than ~65000€/year or are a civil servant. In which case you are entitled for private health care which might be (or in fact is) more expensive but has more options for treatments and some prioritizing on waiting lists and doctor’s appointments.
Family (husband, wife and children) is always insured for free except they are also employed. Children have to pay seperately after reaching age of 25, and if they still study they pay only a low flatrate.
The rate is always 14.6% of gross income except for very low incomes, in which case the employer pays everything, or very high incomes. There is a cap: everything above 65k is not rated – which seems unfair to me.
I assume that’s a product of house price inflation. Or because you count mandatory retirement savings. If you did the same calculation in France for NPV of pension you would probably get a similar or better result
Ok but correct for taxes subtract healthcare, add npv of pensions, dental and child care. I think you would end up much closer maybe even ahead for France. Also mean per capital lies because you have to average in besos and musk. Median is a better metric
Having rich neighbors is great, gdp per Capita seems to be a nice measure.
If you don't make a lot of money in USA you pay basically no taxes... cars are cheap (or were)...
Big problem is govt being terrible with money and overbudensome with regulations, which reduces supply. Think about how many more doctors/specialists we'd have if systems weren't purposefully setup to be ridiculous.
Look into what residency takes. Not everyone has to be an amazing incredible 80hr week doctor. We could easily double supply of doctors...
The American Medical Association restricts med student slots. You could say it’s government but it’s regulatory capture rather than government regulation. Remove Citizen’s United, close the revolving door, and fund congressional research offices so that legislators don’t have to depend on lobbyists for research and writing legislation.
You know, this is the first comment I’ve ever read on government participation in the economy (socialism, if you will) that seems to make great sense to me. I would happily pay into a tax fund that was locked to educating or re-educating participants in the workforce. I like this way better than plain UBI because of the potential for increased dignity, pride and self-esteem.
This is like trying to get govt to invent flight, when instead you just give markets as much power as reasonably possible. Cheap goods and services lead to innovation way better than govt capturing and "redirecting money to their brother's school."
Please don't ignore the thousands and thousands of examples of govt being terrible at this, for the handful of somewhat useful examples of shit sticking to the wall. It's still flinging shit
You know, there's some significant issues that aren't touched on.
Any statement that's all upsides no downsides poorly reflects reality over time.
Or, in other words, if it sounds too good to be true it probably is.
The main one being how would you pay for it?
Basic accounting says the moment population growth stalls you have more outflows than inflows. You can't print money without consequence, and there are other factors that confound these issues further.
Its the ideal of socialism, but the reality is you run into the economic calculation problem. Shortages happen because we live in a world of scarcity, and when they do the system collapses usually causing death (historically).
The Norwegian tax system is not socialist as much as it is _georgist_: Norway taxes natural resource use (mainly extracting oil from oil fields and using waterfalls for power generation) _hard_. This tax policy makes the "more outflows than inflows" calculation a bit more complex than in most countries. The country is not immune to the effects of population decrease, but less so than others.
The main threat to the Norwegian tax system today (in my opinion) is that new industries (fish farming, wind farming) are actively lobbying against georgist tax policies directed at their industries: https://slimemoldtimemold.com/2022/05/17/norway-the-once-and...
Georgism is pretty great, consistently incentivizing people to utilize their land. However, I wonder how much it would change with non-land-based productivity, ie people or AI making money through the internet.
Strict georgism emphasizes taxing limited resources, i.e. resources that can be hogged, preventing others from innovating. If what you're using can be made more plentiful, it's not worth taxing.
For example, taxing your use of transmission capacity would go against georgism: It's possible to make better equipment that transfers bits faster. There are, however, resources that can be hogged on the Internet. For example, domain names: Short (non-trademarked) domain names, e.g. flowers.com, are more valuable than a random string of characters from a lesser known top-level domain, e.g. lrchcu.hat. As there is a limited number of single-word domain names, the owner of the former domain should pay a higher fee or tax for their domain than the owner of the latter.
The economic calculation problem exists form any type of economy regardless of whether it is dezentralized or centralised.
The difference is that a central miscalculation impacts the entire economy while a decentral miscalculation usually only impacts a small area surrounding that person.
If a group of independent people makes a miscalculation like during the global financial crisis then you end up with the same problem it is just less frequent.
I’m still a high earner so I’m fine. I still have approximately $7500/month after my taxes are paid. That’s a lot since all medical care, 1 year parental leave, my kids education from kindergarten through high school etc are “free”, e.g. paid with my taxes.
My point was not to complain but to say to the guy that claims that we need a new system with more wealth distribution that those systems already exist. There are a limit though to how high you can tax someone before they stop producing.
You made a good point. But I don't think people are advocating taxing people like you but the super rich. The disparity between the few super-rich and the poor is so huge in many countries. Wealth that is not being put to use by the super-rich is money wasted. All this hoarded wealth could be put to so much good.
I'm sorry but it's just true that a few people are incredible. Elon musk. Steve jobs. These people are basically worth infinity, their potential and vision is extremely useful to humanity.
Sorry a few make it to the NBA, but everyone can try.
The problem with the super-rich is that they have more money they can spend. The not spending is the problem. Money is good for public welfare only when it is earned and spent. Investments are supposed capitalist solutions to this - to make money "work" for you. But it's a broken circular system that seems to only make the wealthier more wealthy. (It's also becoming dysfunctional with speculations). It doesn't seem to be creating an egalitarian society because people with money often have access to better opportunities. And that's a huge hurdle tomorrow for your kids trying to compete with Elon Musk's or Steve's Jobs kid who are born with wealth.
And if you need that millions throughout your lifetime, that's fine. But imagine you have so much money to spend that you don't really know how to spend it in your lifetime? That's the problem.
There is no amount one couldn't spend -- why are you even saying it this way?
You could get by on like $1,000/mo. Live in a tent, eat rice + protein supplement or whatever, and donate the rest to Africa.
Why don't you do that? If you're posting on this forum: you are in the top 1-5% of the entire world. You have a refrigerator? You should be ashamed and sending that refrigerator to someone who really needs it. You can get by with dry food.
Obviously this is ridiculous. We live in capitalism, which just means _you_ own stuff and control it. If you own a company and that company makes 10,000,000 people happy every day, you're going to make a gorillion dollars. You deserve it, you're literally making that value... ugh..
Then you can do with that whatever you like, just like you can do whatever you like with your refrigerator.
Where's the inherent evil? 10,000,000 people giving $1/day is 365 * $10,000,000 a year in revenue. Where is the evil?! Of course with that money you'll at least put it in the bank, which helps with liquidity, bank runs, funding millions of mortgages, etc... ugh...
I was earning similarly in Europe. The moment I realized how much tax I was paying (51% bracket), I moved to Asia to work remotely. I honestly don’t care what’s being paid from my taxes, but to me that amount felt like theft. I now pay ~20% while being well above 10k after taxes.
This is why comparisons between the US and Europe regarding wages are always fraught. For some people, it makes sense to pay a lot of tax for the benefits it confers. For others, like you and me it seems, it is not really worth it to pay that much tax and not really receive the rewards. But everyone who discusses conflates some people's preferences to suddenly be everyone's preferences, and this is simply not a true comparison.
For one, it's not even clear that democratic politics can work post-AGI. Democracies work because together citizens hold more power than any government or any other individual or collective in society. In the past that was largely expressed as physical power, and why things like gun ownership was important because it allowed the collective to revolt against their leaders, but in more recent times our collective power comes from our economic power.
In a world in which governments can just print money with AGI, then they don't need us. In fact, in this world we're just leaches on state resources and space. And now the dynamic shifts from the state be dependant on the people to the people being dependant on the charity of the state. I see no reason to believe that this would be a stable long-term arrangement.
Also, what you're saying is just hopeium. In reality we don't have this economic system. So AGI is going to be bad for us. And how are you going to change that? Are you going to strike when you're unemployed? Is the government realistically going to be able to tax an AGI company which is doing $100T in revenue 95% of profits? Why wouldn't they just relocate or lobby for lower tax?
Secondly even if we assume by some miracle we can change the economic system and tax companies 95% without them relocating or lobbying to reduce taxes, have you considered that some people actually want to work?
I've been poor most my life. The idea of being a state dependant doesn't really bother me, but what does upset me is that I've spend 20 years of my life skilling up in a profession which will now have no value. And no knowledge professions can ever have value again in post-AGI world.
Perhaps I can go into a manual labour job for a little before manual labour starts being automated too. And then maybe after that the only jobs that will remain are a handful jobs where interaction with real human is valued (hospitality, etc). Perhaps we're just spoilt in the present because we have so many cool jobs. Today people genuinely like working and want to work. I got into coding not because I had to for financial reasons but just because I loved doing it in my spare time so I might as well be paid to do it. But maybe we need to just accept that this was never a sustainable dynamic and that the economic benefits of AGI out weigh us living a fulfilling life...
Well maybe shift to "real world" professions will occur resulting in us addressing abysmal infrastructure and housing situation. I am looking at picking up a trade because of this coming shift.
I don't think people appreciate the mass disruption of a shift like this happening across so many industries all at the same time. This sort of professional shift works when automation comes for a subset of a single sector, but we're looking at an everywhere all at once situation. How many plumbers are we going to need, exactly?
I also don't think people appreciate the absolute social turmoil that will occur as a result of this because of our complete lack of planning for it.
Afraid you won't have a useful job due to the rapid rise of AI replacing vast amounts of knowledge workers? Get to work building guillotines. You won't be able to sell them for very much but you can make up for it in volume.
To the wealth class: Massive amounts of people don't just quietly disappear when they suddenly can't feed or house their families because they've been automated out of a job.
People are very good at creating work. Every time tech creates a paradigm shift and people cry that there will be not enough work, the exact opposite happens.
Exactly, we’ve been automating the living crap out of almost everything for hundreds of years, but employment has never been higher. Automation leads to higher productivity, cheaper goods and services, increased need for technical skills, thus higher wages and higher demand.
Of course there can be some painful periods of adjustment, but that’s often caused by misguided policy trying to hold back the tide and delay the inevitable.
Ultimately yes, full no holds barred human level AI may well render human labour obsolete, but we’re a very long way away from that.
I know some people think LLMs are close to that already, but no, not even remotely close. I do believe strong AI is possible and maybe even inevitable. They’re a huge step forward, and are easily the biggest advance towards strong AI in my lifetime, but these things are just tools.
We have been automating at the beginning of the production chain , mostly.
This is the first automation that targets directly knowledge workers, and hit almost all of them but those in profession where error can cause people deaths.
Traditionally knowledge workers were the bulk of the middle class, because well it takes 30 years to produce one and not all make the cut, so they are paid market prices instead of minimum wages.
And by that nature, knowledge workers cannot reinvent themselves overnight, there will nowhere left to go for them.
Maybe lawyers and medics and a few other can entrenche themselves with legislation, but if you are a knowledge worker in a non union field things look scary.
Real human level strong AI would be that, but the LLMs we have now are nowhere close. They are just a powerful new software tool in the hands of specialists.
Maybe GPT10 might get there, but I suspect we’ll quickly reach diminishing returns with current and near future architectures.
This is a real hand wavy way to look at it. How about on the individual level? How is an individual affected by this and can you put yourself in their shoes?
I can’t tell you which individual people will lose their jobs, or even which specific jobs will end up being cut and why. Can you? We’re both just making different estimates of the likely overall effects. I’m basing mine in the known historical effects of automation on economies and employment, and the fact that previous arguments that were all doomed by it have every single time turned out to be false.
No, nobody can and that’s the point. Except the flaw in your thinking is your applying what happened in the past to the present. Nobody has every automated a human brain before, they mostly automated muscles away. This time is different so therefore you cannot assume that since a welding robot didn’t destroy the world that AI won’t. Automation and AI are not the same and we should quit calling it as such.
I certainly won’t claim that capitalism is immune from abuses or failures. It’s undeniable that it has its failures. But criticising its failures is one thing, while criticising it as a failure is another. To make the latter claim credibly you’d need to argue for a better alternative that either further minimises or eliminates the flaws. What is it?
When people cry that there will be not enough work, the exact opposite happens.
Nevermind that these people aren't crybabies - and that it is incredible condescending to paint them as such.
More fundamentally - what you're asserting as a self-evident fact is massively contradicted by what is probably the single largest sea change in many Western countries in the last 50 years - the systemic disappearance of solid middle-class jobs (and at least some form of community in many places), due exactly to these nifty "paradigm shifts" you are referring to.
Right. The last time a labor saving device came around, letting you do in 2 hours what it used to take 8 to do, it didn't give you 6 hours of vacation, it just meant you were more productive over your 8 hour day. If your job is now 90% "copy and paste into ChatGPT", you're still getting paid to know what to type into it.
Then again, I'm also reminded of a story of a homebuilder, hiring two workers. Together they held up the material and one of them measured the hypotenuse. Well, after someone showed him the Pythagorean theorem, the boss no longer needed the two workers to hold the materials up, and so sent one of them home. That day's labor market didn't expand to hire the guy who's job was replaced by a calculator. Does that extrapolate to the whole labor market, over a longer period of time, given a calculator for words?
In the US at least we have used every technology that increases productivity to keep hours of labor constant and make the rich richer. Millions of Wal-Mart workers have to do a year of hard labor just to earn the cost of a set of new tires for the CEO's 10th supercar.
> Millions of Wal-Mart workers have to do a year of hard labor
Working at Wal-Mart would be miserable in many ways, however nothing I've ever seen their employees do is even 10% of what I'd call "hard labor". Probably even their warehouses are not even close to farm/ranch/factory labor people associate with that term.
These jobs are not hard on the back, they are hard on the soul. Tilling a field can feel rewarding at the end of the day. Dealing with the living nightmare that is most Walmart shoppers is soul crushing.
Your viewpoint is rather callous. Just standing on your feet bored out of your mind can make even the most hardy miserable.
Agreed. I don’t know if I could be on my feet 8 hours a day like when I worked retail. When you work in a big box store it’s easy to walk 8+ miles a day.
If the Walmart employees aren't needed, Walmart would just fire them. They're still there because their work is still required, as people are continuing to buy more stuff from Walmart. It's not some conspiracy to keep hours of labor consistent, the workers aren't getting paid 8 hours just for no reason.
First of all the LM002 is not what many would call a "Supercar". At least not modern day. An actual supercar, the Ferrari 296GTB, uses Michelin Pilot Sport 4S tires, the same tires you would put on a Porsche. Or your WRX. Further I looked up the CEO of walmart, he doesn't drive an LM002
Even the Lamborhini Revuelto uses Bridgestone Potenza Sport tires which clocks in at about $500/each
I'd say biggest displacement would be in
IT,
Insurance/Financial Services,
Creative,
legal,
Thats not even 10% of the work force
and it would prob. take a decade for it to fully play out.
It is only a displacement if one assume that the total demand will remain the same, that professionals will be replaced by the cheaper AI while the total volume of work needing to be done remains steady. Take law, there are a great many legal activities that are not done today because of the cost of entry. AI will make lawyers cheaper. That will meant previous tasks that were forgone due to costs will now be financially possible. A small claim that wasn't worth a lawyer's time today will, in a future of cheaper AI-supported lawyers, be financial viable. Complex legal structures like trusts or life estates, once only available to the élite, may now be available to all. The next result may be an actual increase in the demand for lawyers as the total pool of work increases, both AI-possible and that which AI cannot do.
So too for complex accounting/insurance structures.
This isn’t the greatest example as there’s some glaring issues. With more small claims taking up the court’s time then how will we have time to litigate actual important matters? Will we then have to result to AI judges? Slippery slope.
Also customer support, and various flavors of clerical and administrative work.
Under the BLS classification scheme, these jobs are sprinkled around under various industrial categories such as medical, logistics, business services, etc. they add up to a large number of jobs in the aggregate (probably another 10%)
I think we still do not know exactly how it will shape our sociaty, but one thing is for sure, the products businesses will make with the help of AI, people have to buy them in the end. If they have no money how will people using AI benefit.
i did that, i got injured at work and now can't do physical labor. Trades are hell on the body and bosses will toss you aside without any care. Join a Union if you're gonna go into the trades, i would've had protection and better safety.
I took so many people to the ER for work injuries that were preventable but the bosses skimp on everything.
Risk of injury comes from two things: Environment and stresses on the body.
Environmental risks can be mitigated, if the job location inherently has risks, you will be better off with a regulated industry where the regulations have teeth, and probably in a union. Stresses on the body are largely mitigated by having a job that takes more brain than back, but watch out for repetitive motion stuff and mitigate that yourself.
Mostly in the trades you get paid more for some mix of a) having in-demand skills and experience that aren't easy to acquire fast, b) putting up with unpleasant environments, or c) accepting risks. You can probably trade off c against a mix of a) and b).
So for example being a tool and die maker in general is way safer than being a faller. Watch for industry specific stuff too. Kicking carpet is more pleasant and less dangerous than electrical, but it won't pay well and your knees are likely screwed by your mid 40s.
Robotics will rapidly pick up improved capabilities. With so many people out of work and so much automation being consolidated, what do you think all the entrepreneurs and researchers will look to next? It will be breakthroughs and efficiency improvements in robotics .
I think this "learn a trade" plan has maybe 5 years max. By then the trades will also be automated.
I'm not a gambling man but if I was I would put a very large amount of my net worth on a bet that no trades will be automated in 5 years time. Not a single one.
I think trades will be around for a century. The problem is dealing with crazy existing stuff, like houses that are not to code and have been repaired by the last 3 owners, all of whom made it up as they went. Good trades people are able to figure out what the last idiot was thinking, know how it is supposed to work, and can make it work (without callbacks) for a long time with minimal intervention.
I remember a college professor who cashed out his retirement in the mid-1990's to start his own online college. He went broke in less than a decade, and we still have not removed professors from the colleges.
As a teacher, I do think that ChatGPT will replace most textbooks and teachers, but I don't know how long that will take.
Progress is slower in the world of atoms than in the world of information. I watched the progress from the first DARPA Grand Challenge for self-driving cars (2004, no car made it to the finish line) to the Urban Challenge in 2007 (many cars succeeded in a much more complicated environment) and thought that self driving vehicles would soon be commercialized. But there are 10,000 "last 1%" cases left to handle and we still don't have good enough systems to replace truck drivers or cab drivers today. Replacing jobs like plumber or electrician looks even harder than self driving vehicles because it requires far more intricate physical manipulation and perception than driving on public roads.
I mean I think that's with every system a problem. Not just ours. Wealth distribution has been a challenge since we've moved away from spending our day solely focused on gathering food / farming. Every shock to our current system will take time to adjust.
Probably not, but Norway is generally an anomaly. It's got massive natural resource wealth, a small homogeneous population, and is surrounded by allies and falls under the US security umbrella
> I mean I think that's with every system a problem. Not just ours.
This doesn't mean that different economic systems have equivalent or comparable problems. Just like you can have a worse economic system than today's global capitalism, you could, in principle, have better systems.
Capitalism is not an economic system, it is a description of fundamental economics.
Countries can have a highly regulated form of capitalism where trade and ownership is strictly controlled… and they’re often called socialist or communist, or a laissez faire system.
However, so long as people are using land, buildings structures, designing equipment… the laws of capitalism will apply.
Capitalism isn’t a fundamental law like the speed of light or thermodynamics.
We can use other systems that suit our goals better. Even if it’s a better form of capitalism than what we’re dealing with now.
This post-monetarist form of capitalism is killing people and this planet and enriching but a few. That’s not the kind of society most people want. A matter of time before there are enough have-nots and upheaval becomes a real problem for the capital owners.
Capitalism is too broad a term to be useful in these conversations.
At it’s core capitalism just means that private individuals can own property, instead of the state owning everything. Which is absolutely critical for a free society. It’s paramount that individuals not be dependant on a ruling class for survival.
Ownership is a term that is loaded and the argument between socialism and capitalism is actually not really helpful.
For instance, if we removed the concept of capital and implemented socialism, there would still be a concept of "responsibility for". So if there were community bicycles, individuals would still have responsibility if they threw the bicycles in a lake. The community officially "owned" the bicycles, and the individual acted against the community's best interests.
Capitalism as written about by Adam Smith seeks to solve the same problem by putting the "ownership" in the hands of the individual, so that the individual is given incentive to care and maintain the bike.
These are both potentially-effective systems that seek to solve the problem of "who's responsible for this bicycle". There are trade-offs for each.
When we simplify complex market-based problems into choices between either capitalism or socialism, we have created nice ways to describe the problem, but neither of them serves as an effective solution to the problem.
For the solution, we have to dig deeper and that means not being beholden to ideologies that can prevent us from seeing good solutions.
The problem with ownership is that it isn't that easy.
With land people don't own the land itself they only have exclusive usage rights for a specific period of time. Once that time is over they are no longer responsible. Thus even with private ownership you still can have the tragedy of the commons problem, it is just divided over time instead of space.
The most common example is soil depletion from industrialized agriculture.
If you wanted to solve this problem you would need a regulatory body that inspects the quality of the soil and fines people who degrade it. Governance becomes essential
to balance the micro and macro economy.
The concept of property has been warped to include the value of shares of a corporation, whose value is generated by the labor of its employees. This is the primary way the richest people steal wealth from labor.
Only if you believe in the Labor Theory of Value, which most don't. If I own a ship that's going on some expedition (as how shares originally started), I raise capital and reduce risk by issuing shares that people can buy. I have to, well, share my wealth but I have more money now to do the expedition. Corporations are just bigger versions of the same idea, they're still run by people, any of whom can decide not to work there anymore, for better or worse.
What you and other students of Karl Marx always ignore is the fact that if company owners was not allowed to earn profit then there would be no companies founded, meaning that the workers would not have jobs.
They can do that, nothing stops people from setting up co-ops today, I've been in one as well in fact. But at the same time, if I'm making something lucrative, I'd want to profit from it. That other people I hire are willing to work for the wage I give them is their problem, since if they don't like the wage, they can always go elsewhere (given that they are skilled workers, not workers who can find no other job in some company town or something).
Your argument possesses a fundamental mistake that most venture capitalists make: that the demand is infinitely elastic but supply is completely fixed; in other words, the manufacturers being able to perfectly impose what consumers want to consume.
I don't see where I imply that supply is fixed. I don't think that makes sense even from a VC point of view, since the company they fund is itself another manufacturer or producer of goods, thereby increasing the supply.
What you and other billionaire boot-lickers ignore is that earning $10 million from starting a company is very reasonable, "earning" $100 billion is just stealing from many thousands of employees. We really should NOT need a logarithmic scale when talking about wealth inequality.
Except the labour theory of value is utter nonsense. It lead Marx to argue that railway workers, helping transport goods to where they were needed, contributed negative value and were parasitic on manufacturing labour.
Ideas, leadership and capital are vital to a functioning economy. Every time a system has been set up that denied that, and it has been tried many times, the results were catastrophic. In several cases tens of millions of people dead catastrophic.
Indeed. Eventually the interests of capital owners force them to fail. Like when the CIA backed a military coup by a fascist general to overthrow a democratically elected socialist. Because US investments were threatened.
No economic system can mitigate toxic politics. Regulatory or political capture by economic interests is always a threat. As is political seizure of economic assets or resources. These are human failings you find in any system. This is why rule of law is so important.
A society doesn't simply implement socialism (or any system) and call it a utopia. There will always be forces and counter-forces. Fascism will continue to find a way back into any system it can.
We can both completely completely agree on both points. There are no magic wands that will solve corruption and rent seeking. These are both human flaws. I’m not even against a dose of socially managed resources and services where it makes sense. Cheers.
Cheers! Indeed a bit of planning can work, even in a mostly capitalist system. Take WalMart as an example. It's annual revenues dwarf the GDP of many small countries. And yet it is centrally managed, planned, and rather efficient!
The Ludlow Massacre was a mass killing perpetrated by anti-striker militia during the Colorado Coalfield War. Soldiers from the Colorado National Guard and private guards employed by Colorado Fuel and Iron Company (CF&I) attacked a tent colony of roughly 1,200 striking coal miners and their families in Ludlow, Colorado, on April 20, 1914. Approximately 21 people, including miners' wives and children, were killed. John D. Rockefeller Jr., a part-owner of CF&I who had recently appeared before a United States congressional hearing on the strikes, was widely blamed for having orchestrated the massacre.[6][7]
The massacre was the seminal event of the 1913–1914 Colorado Coalfield War, which began with a general United Mine Workers of America strike against poor labor conditions in CF&I's southern Colorado coal mines.[8] The strike was organized by miners working for the Rocky Mountain Fuel Company and Victor-American Fuel Company. Ludlow was the deadliest single incident during the Colorado Coalfield War and spurred a ten-day period of heightened violence throughout Colorado. In retaliation for the massacre at Ludlow, bands of armed miners attacked dozens of anti-union establishments, destroying property and engaging in several skirmishes with the Colorado National Guard along a 225-mile (362 km) front from Trinidad to Louisville.[6] From the strike's beginning in September 1913 to intervention by federal soldiers under President Woodrow Wilson's orders on April 29, 1914, an estimated 69 to 199 people were killed during the strike. Historian Thomas G. Andrews has called it the "deadliest strike in the history of the United States."[2]: 1
The Ludlow Massacre was a watershed moment in American labor relations. Socialist historian Howard Zinn described it as "the culminating act of perhaps the most violent struggle between corporate power and laboring men in American history".[9] Congress responded to public outrage by directing the House Committee on Mines and Mining to investigate the events.[10] Its report, published in 1915, was influential in promoting child labor laws and an eight-hour work day. The Ludlow townsite and the adjacent location of the tent colony, 18 miles (29 km) northwest of Trinidad, Colorado, is now a ghost town. The massacre site is owned by the United Mine Workers of America, which erected a granite monument in memory of those who died that day.[11] The Ludlow tent colony site was designated a National Historic Landmark on January 16, 2009, and dedicated on June 28, 2009.[11] Subsequent investigations immediately following the massacre and modern archeological efforts largely support some of the strikers' accounts of the event.[12]
It’s inexorably true that means of production control the outputs.
It’s unavoidable that whoever has power over production has power over those who rely on those outputs.
Unless you’re advocating for the destruction of factories, the razing of homes, etc. you’re in favor of capital. We’re just discussing who is going to control the capital.
> However, so long as people are using land, buildings structures, designing equipment… the laws of capitalism will apply.
Capitalism is the system
where someone can claim ownership of land/buildings/ideas(typically due to prior ownership) aka "capital". If the laws don't allow someone to make and hold that claim of private ownership, how would the "laws of capitalism" still apply?
> Capitalism is the system where someone can claim ownership of land/buildings/ideas(typically due to prior ownership)
Typically due to paying someone to invent/build them, then continuing to capitalize on essentially someone's else work.
That's the problem. I think we would be in much better situation if the person who worked on something reaped majority of benefits, and not boss of their boss.
Instead we have IP producers needing to produce thru their whole productive life, while having their IP ownership assigned to corporations because that's what their employment contract allows, and nobody else in society being able to benefit (without paying not-the-author of it), even tho near everything relies on what came before.
That then can be used by corporations either long enough to stifle innovation and competition (patents), or even long enough that nobody involved is alive anymore (copyright law), all while paying far lower taxes than people they hire.
Like, capitalism might have some problems but they are by far exacerbated by how law around it works. Any technology that increases performance by far benefits the owners of company the most and they pay less taxes on top of that.
>Capitalism is not an economic system, it is a description of fundamental economics
Silvio Gesell has developed an economic system inspired by Darwin. I don't mean social Darwinism, I mean that he deconstructs the economy down to self preservation and group preservation instincts which are biological necessities.
Self preservation is necessary to survive. A biological organism that does not self preserve will be selected out. This means that self preservation instincts represent egoism.
You might now say that this is the end, capitalism has won, except there is also group preservation.
Group preservation requires self preservation as a prerequisite. If you cannot meaningfully self preserve, you will most likely contribute nothing to group preservation as there aren't many situations where dying outweighs the cost of raising a member of the group.
This means self preservation instincts play a significant role all the way until they start threatening group preservation.
An organism that exclusively specializes in self preservation would always be a lone wolf with no socialization. The problem with this theory is that it would imply subsistence which is the opposite of capitalism. In other words, capitalism cannot be the result of simple egoism and self preservation because people would simply leave the capitalist society for the sake of self preservation if it were to become too stressful.
Thus there must be a significant group preservation instinct in humans and they have been evolved to survive in groups. In other words, capitalism has to leverage group preservation instincts somehow and therefore it is just another flavor of socialism or communism except in favour of people with capital.
Now, you can take it too far and entirely rely on group preservation instincts like communists claim but that doesn't work in practice either as self preservation overrides group preservation. Only people who have their basic needs met can engage in altruism.
Thus you can't expect a society consisting exclusively of altruists or egoists. Instead you would expect evolution to hit just the right balance between the two and that would imply the absence of both capitalism and socialism. It means both are an aberration that cannot be explained biologically.
Yes, that would imply that people can choose to participate in a market economy but it doesn't mean they have to and market economies don't have to be capitalist.
>Capitalism is not an economic system, it is a description of fundamental economics.
Theoretical economists have no concept of capitalism except maybe Keynes. In classical and neo classic economic theory there is no such thing as "capitalism". In theory it doesn't exist. There is a market economy with zero coercion and it does not intrinsically favor capital. You can't get richer through unfair means or corruption in these models either.
The gaps between the model and the real world are then filled with dogma and ideology. For example, you can just say that a positive return on capital represents a voluntary high time preference even if the return is higher than what would bring the economy into equilibrium.
The real world starts exhibiting cycles that make no sense in the model, meh. Let's claim capitalism is a constant of the universe even though biological dynamics imply the opposite.
> Wealth distribution has been a challenge since we've moved away from spending our day solely focused on gathering food / farming.
Have you ever considered that this may be due to the fact that our brains evolved to exist in a world where our day is largely focused on gathering food? We're not well-equipped to exist in other modes.
I said, "majority of the day focused on gathering food, not "spent gathering food". If this seems like an arbitrary distinction, allow me to provide an analogy. Most teenage boys spend the majority of their day focused on having sex, but very few of them spend the majority of their day actually having sex (if they're even having sex at all).
As for a citation, ask anyone who's spent any amount of their life with not enough food available. If you ask them how much of their time is spent focused on getting food or thinking about food, or worrying about food, they'll probably tell you "most of it".
It certainly depends much on the regional setting. Humans pushed to the boundaries of landscapes which support their existence. If you are a hunter gatherer in fertile jungle setting you might make do with 2 or 3h per day of hunting or gathering. If you live further north or south or in more arid regions that might take more time.
If we could just stop being economically gaslighted it would help.
The economic system can't be simultaneously unproductive enough to require us to keep raising the retirement age and so productive that job loss is a big problem.
It is possible that a political war on labor is being waged at both ends.
It's possible to have certain things be abundant and other things be scarce simultaneously, because technology doesn't make everything abundant at the same time. That means certain types of labor are abundant and others scarce at the same time as well.
There may be a war on certain kinds of labor but having to raise the retirement age and having job losses from tech aren't evidence of it.
>Yet you internalized a belief that we have to do it [keep laboring] when so much of the labor it would produce more of is already abundant. Why?
If there is so much abundance and labor isn't needed, why is almost every country on Earth currently experiencing food inflation? Abundance would mean prices go down, not up. We would need fewer farmers, not more.
Before you say it's being caused by corporate greed and price gouging, this is why I said globally. If for example Vietnam locally produces rice, and it's not even a capitalist country, there shouldn't be rice inflation there. Yet there is, and rice farmers in Vietnam aren't retiring because human labor and rice are so abundant.
Why pretend that just because some things have become abundant with technology, we can make society wide proclamations about labor no longer being needed?
It seems more like war on paying people fair wage for the work. Suits don't want to live in age where shit job doesn't come with shit pay coz that cuts into profits.
The changing demographics is what causes the retirement age to be increased.
In the 1960's, the average lifespan was in the 60s. So a retirement age of 65 meant that around half of retirees would die before collecting retirement.
Now the average lifespan is 80. And the median age of the population is older than ever.
Not really much to do with an "unproductive" population. Except that retirees are unproductive I guess.
>Not really much to do with an "unproductive" population.
If we pretended that there had been 0% increase in economic productivity since then then, then yes, changing demographics are a problem.
This is indeed, what most justifications of increasing the retirement age quietly assume. It's probably quite easy to assume because the % of increase in productivity captured by the working class since 1970s as wealth has actually been quite small.
Compounded economic growth since the 1960s has, I think, been something of the order of 200% though.
>In the 1960's, the average lifespan was in the 60s>So a retirement age of 65 meant that around half of retirees would die before collecting retirement.
For Switzerland life expectancy for men went from 26 years at 50 years old in 1981 to 33.1 at the same age in 2021. That's more than 7 years. (At birth it increased from 72.4 to 81.6 at bit more than 9 years).
So can we now please stop to mention all the time that the increase in life expectancy is only caused by infant mortality reduction when it's clearly not the case?
> So can we now please stop to mention all the time that the increase in life expectancy is only caused by infant mortality reduction when it's clearly not the case?
My point was in regards to the GP:
>> In the 1960's, the average lifespan was in the 60s. So a retirement age of 65 meant that around half of retirees would die before collecting retirement.
>> Now the average lifespan is 80. And the median age of the population is older than ever.
This makes it look like the pension system is doomed to fail due to a massive increase in the average lifespan today compared to earlier.
> That's more than 7 years.
If you're looking to balance the pension system, people just need to work 3.5 years longer given that increase.
It's gone from about 70 for average people in 1920 (when life expectancy was at a local minimum, probably due to pollutants and terrible diet) to about 80, not counting infant mortality. That still means tripling the years in which someone is retired.
If you look at the pension system today, people work for about 40 years, and are retired for about 20 years.
If the average life expectancy for the retirees increases by 1 year, they'd have to work 6 months longer to keep the system balanced with those numbers.
I am currently reading the late Daly’s 2014 book “From Uneconomic Growth to a Steady-State Economy” that seems to address exactly your concern for a more fairly distributed economic system. A real eye-opener that would require us to change three things to build a more sustainable economy and future:
(1) stop fractional reserve banking and nationalize money again to avoid the very quantitative easing/tightening fiasco we are seeing today,
(2) measure economic progress with a quality of life index instead of GDP to accurately reflect the cost of products/resources and put more emphasis on life quality improving services, and
(3) replace the current international trade rules and system run by the IMF with a more equitable system where capital costs are accurately reflected at the source to avoid “outsourcing” problems to third world continues.
While all three changes are difficult to achieve in our current society, I am amazed at how clearly Daly’s life work can outline how we could build a much more sustainable economy and healthier society.
Maybe his amazing last summary book is of interest to others on HN.
I am sorry but fractional reserve banking isn't the problem, nor is debt based money the problem. You can't solve the problem without allowing interest rates to be negative when people want to pay off their debts at a faster rate than people wanting to spend off their credits/deposits.
The problem is quite simple. Money has no maturity but debt has a deadline. This asymmetry causes problems regardless of whether you have a gold standard, full reserve fiat or fractional reserve fiat.
In other words, if you can fix the asymmetry or eliminate the zero lower bound it doesn't actually matter what form your money takes.
I don’t think Daly is suggesting to move away from debt as an instrument in his work, only to establish a 100% reserve system for commercial banks, including the Fed. He was suggesting to nationalize money supply via the Treasury, to avoid bank runs and fiascos like they happened just now to CS and SVB.
Apparently, this was already the direction of thought among some economists in the 1920s (like Frank Knight and Irving Fisher), but then got overruled by the eternal growth mindset that evolved during the Great Depression (which Daly claims leads to “uneconomic” growth). Printing money as an instrument should very much be available - but only to the Government/Treasury.
Just to expand on the above, as two days later I now feel it is hard to understand how my reply is related to imtringued‘s last paragraph (“if you can fix the asymmetry or eliminate the zero lower bound it doesn't actually matter what form your money takes”):
If you don’t allow banks to “print debt” out of thin air by eliminating fractional reserve banking, as Daly suggested in his work, I believe you eliminate that asymmetry. Actual money is lent, actual money has to be returned.
The question that remains then is if it is valid to ask for interest on that money. But I believe that is acceptable, and the rate might be set to 0% or even negative in the right circumstances.
The fact that anyone today thinks that any other economic system we’ve ever tried is any better than the one we have is a damning indictment of our education system.
The fact that USA's brand of late-stage capitalism is even considered capitalism is an even more damning indictment of our education system.
Somewhere between Feudalism and Karl Marx, Adam Smith is spinning in his grave. How much we don't have capitalism and are living, globally, under an oligopoly, replete with robber barons in tech clothes; one can only laugh at.
The amount of misery under "capitalism" says there's got to be a better way.
I’m open to suggestions, at the end of the day it’s what works that matters, it’s just that every other system ever tried is minimum an order of magnitude worse. I’m not particularly a fan of the ‘red in tooth and claw’ brand of capitalism in the US. It’s a bit raw for me, but undeniably very dynamic.
Meanwhile in my lifetime capitalism has raised hundreds of millions of people out of poverty and into solidly middle class lifestyles globally.
My wife is Chinese so I’ve seen first hand how economic liberalisation has transformed that country. The Chinese brand of capitalism is severely flawed, largely due to an almost nonexistent rule of law, but compared to what they had before its night and day. It’s a shame the CCP seems to be thoroughly mismanaging it at the moment.
Mayor Unterguggenberger introduced a demurrage currency in Wörgl during the great depression before WW2. He "printed" 10000 shilling worth of Arbeitsbestätigungsscheine (work confirmation coupons). The coupons are valid until a certain period, then you have buy a stamp and glue it on. This approximates a -5% interest rate. People didn't hoard the coupons and the town accepted them for tax payments. The town was out of debt within a year and unemployment has shrunk by double digit percentages. The depression was effectively over and all it took was the equivalent of food stamps/unemployment benefits except transferrable between businesses and consumers with a demurrage fee.
The system doesn't have to be adopted by every business or citizen. For instance, 10% of unemployment benefits could be paid out as a demurrage currency with tax acceptance and you would see large scale welfare benefits with almost no burden on the general population.
The only burden of this system is juggling two different currencies and an insignificant 5% annual fee on the issued demurrage money supply. If pay out 10% of unemployment benefits or 15 billion dollars it would only cost 750 million dollars in the liquidity fee and that is assuming the money doesn't immediately go back to the government for tax payments at which point the costs keep shrinking and shrinking.
The problems with the Chinese brand of capitalism and the USA brand of capitalism is that both are called capitalism and the general public hasn't developed a better language for debating the nuances of each. If anyone dare say that the USA brand of capitalism is imperfect, they're automatically assumed to be a communist (I'm not even kidding - https://news.ycombinator.com/item?id=35497892), which totally misses all nuance.
The claim that it's capitalism that has raised hundreds of millions of people out of poverty is a common one, but it's our technology that's advanced. If we were still living under feudalism and the industrial revolution and the Internet happened, hundreds of millions of lives would still have transformed. Thanks to John Deere and Monsanto and the like, billions of lives have been raised up from subsistence farming to where we are today. There's the argument that we wouldn't have this technology without capitalism, and the length of the Egyptian and Roman empires without the Internet lend credence to this possibility, but it's also impossible to deny that we've never and can't test whether a system other than capitalism wouldn't also lift millions out of poverty, given the same advancements in technology.
It turns out that centralized, long-term planning is necessary for certain advancements. Eisenhower's US highway system, for example. Or the Manhattan project. Yes, the market is great for a large number of things. One of my most favorite is the food bank story, where they created their own internal market, with credits, and used that to more efficiently organize actors and allocate resources *.
I'm also just done pretending that USA's brand of capitalism is perfect, or that we have a free market in the first place in places where we don't (eg pharmaceuticals) but still try to run it in a capitalistic way, and then get surprised when someone like Martin Shkreli plays the game according to the rules, buys a company with a monopoly on a product, and then raises prices when that's just the rules we've set up for ourselves. Yes he went to jail, but that wasn't because he raised prices on Daraprim, but because he was also running a ponzi scheme and the attention made that finally catch up to him.
We're not going to get to a better system by upending what's been working well enough, but with smaller, more specific changes to the existing system to make it work better. Framing any changes to the system as a moral upheaval and equivalent to communism is the problem. We can have a better system. Yes, some of it involves sharing with others and caring for your fellow human. Some of those humans don't look like you and you may not like them. That's okay, you don't have to. There are people I don't like either. But what we have that works for some, also isn't working for others. When baby food is locked up because people are stealing it, if we assume it's mostly not being stolen and used for nefarious purposes, like cutting cocaine; if we assume people are stealing baby formula to feed babies, and that's criminal behavior according to the rules of our society; stepping back and looking at that from first principles, that all the rules of society and capitalism are for the benefit of humanity. If we really stop and think about that, something has gone wrong.
> The claim that it's capitalism that has raised hundreds of millions of people out of poverty is a common one, but it's our technology that's advanced.
The main factor there was economic liberalisation in south east Asia. Mainly China of course but not only. There was nothing inevitable about that, it was a political decision. The Soviet Union didn’t do it, North Korea didn’t do it, but China had Deng Xioping and he did do it. He or someone else could have easily gone a different way. My wife is Chinese and I’ve visited frequently in the last 20 years and seen the transformation for myself. My wife’s family there are among those who went from grinding poverty to a comfortable lifestyle owning several properties with 2 cars.
Owning properties privately, in China, before Deng that would have been unimaginable. My wife’s sister even owns shares. It’s capitalism gone mad.
Proto capitalism is what lead up to feudalism. The Roman empire didn't have modern capitalism with banking, company shares and insolvency but what they did have is a silver/gold standard with debt bondage. Debt bondage is still a thing in Pakistan and the dynamic is exactly the same. You borrow a little money, the interest payments become overwhelming, you are forced to work on behalf of the creditor who can decide your wage and the interest rate.and whether they pay you in food and shelter or in money. There is no reason why they wouldn't abuse this power.
You see it all begins very benign. A farmer has a bad harvest. He needs to bridge over this year until the next harvest. So he borrows money with interest. When the next harvest fails then he becomes unable to pay and is forced to sell his land and perversively, hired to work on his own land. He has functionally become a serf. All it takes is for this to spread to the rest of society and you end up with feudalism.
In other words, feudalism is what happens when proto capitalism is exaggerated to an extreme extent.
If you were to exaggerate modern capitalism I am not sure what would happen. Maybe hyperinflation, maybe world war 3, maybe a reform of the banking system, maybe mass starvation or maybe a revolution or maybe modern feudalism except serfs aren't allowed to own intellectual property or shares in companies.
So no, I don't think the problem is that we don't have capitalism. We clearly have more capitalism than we want or need. Robber barons are an intrinsic part of capitalism.
The answer is a market economy without capitalism. I don't even see why anyone would care about capital obsession in a free market anyway. That sounds inherently autocratic. At some point in the capital accumulation process one person owns the entire economy, how does that not make them a monarch eventually?
It actually seems to be about distributing power as much as possible. The effort right now with LLMs such as by Microsoft and Google is to rush to make them available to as many people as possible as cheaply as possible, even for free. That’s because this way they can create the maximum amount of value as efficiently as possible, with MS and Google skimming off the top of it all through advertising.
I’m sure premium private services will be a thing, but right now the sheer scale of the mass market seems to be a powerful democratising force. Let’s hope it stays that way.
I'm OK with accepting a certain amount of it. It's a thing. Is there a configuration under which there is no misery? What's the minimum possible amount of misery we could hope to achieve? My problem is that when people's thinking tends to go along the lines of "misery is bad therefore we must eliminate all of it" they come to conclusions that are counterproductive because they're trying to break the laws of physics.
If I came to a ludicrous conclusion, like we should eat babies because that would reduce misery, then attack that ludicrous conclusion. But being pro-misery because some people make bad conclusions from being against misery is, well, ludicrous.
The fact that you jump straight to Communism (without having the balls to openly say it) when nobody even mentioned it, that's a damning indictment of your education system. Or religious doctrine, I should say.
Ever thought that maybe Capitalism is just a small step in human history and that we can definitely do better? I wonder what happened to innovation, is it fine only as long as it doesn't threaten the status quo that keeps you complacent?
There are loads of other economic systems. Feudalism, oligarchy, tribal pastoralism, you name it.
I was mainly thinking in terms of critiquing the idea that value is created by labour, since HyperSane mentioned it twice in comments.
It happens that the labour theory of value in central to Marx but it’s not exclusive to him. Adam Smith indulged a lesser form of it in one of his uncharacteristic slip ups in economic theory. However it is in Marx that it achieves its most vertiginous heights of absurdity, and through his disciples that the most damage was done by it.
There is a direct causal line from the LTV and some of the direst economic disasters in human history. The most egregious case, despite some strong rival examples in Soviet Russia, is probably Mao’s Great Leap Forward which among other things fetishised steel production. Production creates value and steel is the most important economic product, so everybody should make steel.
It’s the damage the LTV caused itself that I was talking about. Communism is a political project associated with it but not directly what I had in mind.
As for innovation, I’m all for it. Capitalism maximises individual freedom by putting ownership of capital and rights of self determination of labour directly into the hands of citizens. By maximising individual economic freedom it maximises opportunities for economic innovation. This is why free market capitalist economies are so creative and dynamic.
Capitalism is responsible for chattel slavery in the Americas, the genocide of untold native populations in Asia, Africa, Ireland, the South Pacific and the Americas; famines and environmental destruction around the world; destroyed the stability of most of Africa, the Middle East, Central and South America; and it has rewarded bad behavior like pumping so much carbon into the atmosphere that we have irreversibly altered the climate of the entire planet. That's literally just skimming the surface - tetraethyl lead, CFCs, an anthology of chemical-related explosions and spills, the great Pacific garbage patch, depleted fisheries around the globe, the obesity crisis, the opioid crisis, the homelessness crisis, and so on.
I still stan (a version of) capitalism, I agree it's better than the other systems, but I do always get a giggle when people act like communism caused the worst disasters in history. They're not great, to be sure, but at least the Communists were mostly killing their own people through incompetence rather instead of killing the entire planet for avarice. It's humans all the way down, doesn't matter what system. Either you have accountability, or you don't and if you don't bad things happen.
Are you aware of the utterly catastrophic environmental devastation caused by the Soviet Union, and to this day by Chinese state industries? This is the problem with undemocratic centrally planned systems, with state controlled media. Complete lack of accountability.
Who's "we"? The West? The US? Humans? If it's the latter, we have had (and have) better - check out the Islamic financial system. It does have certain "capitalistic" principles (competition, no taxation by the government) but also places red lines against immoral practices. Best of all worlds basically.
Who said anything about knowing any good alternatives to the current system that could be switched to? If it was that easy, some country would have done it already, and they’d be winning the OECD.
I think the suggestion is rather that we are morally compelled as a society, to invest real effort into inventing something new to replace neoliberal capitalism.
States could, for example, be sponsoring experiments to validate new economic models, through e.g. low-barrier-to-entry applications for charter cities and other autonomous zones, as long as the applicant can show that 1. there is a novel economic model at play, and that 2. the zone is being carefully monitored to collect data for analysis by the Economics department of a major academic institution.
Economic experiments are going on all the time. Basic income, profit sharing, kibutz, all sorts. It’s not as if every western country is economically identical either. Neoliberal capitalism runs the spectrum from America to Scandinavia, via France.
One of the major advantages of neoliberal capitalism is it’s not exclusionary of alternative forms of economic organisation. It can exist very well alongside state capitalism, or almost anything else. After all individual freedom to organise as you choose is precisely its core characteristic.
If you want to establish a workers collective, or whatever you like, there really aren’t any barriers to doing so. In fact they do exist, some have been very successful. That’s great, but the fact that they are vanishingly rare I think says a lot more about the inherent problems with such systems than they do about capitalism.
This problem isn’t specific to AI. Luddites were concerned about machines taking their jobs. Marx recognized the role of “capital” (of which AI is the intellectual type) in suppressing the incomes of the working class relative to the owning class. Both Marx and the Luddites conceived of different solutions.
One solution (the Luddite one) is to eschew the technology. If nobody adopts the technology, nobody has to, but nobody can benefit. On the contrary, if anyone adopts the technology, all can benefit, but all also have to suffer the negative impacts. Without everyone on board, the Luddite solution cannot work.
Marx saw a different solution: communism. If the state owns the means of production, the working class and owning class benefit equally. It’s unlikely that we ever move toward this, in my opinion, due to the other issues inherent to communism (unfair (from the perspective of most policy makers) distribution of resources, corruption, etc.).
We need to find a new solution; one which enables people to benefit from technology while minimizing the downsides, or at least localizing the downsides to those who choose to adopt it. Right now we have, IMO, one of the worst situations of both worlds: privatized benefits with publicized costs. For instance, any taxpayer funded bailout.
Eschewing technology is not what the Luddites were initially after. At first they asked for a minimum wage, minimum labour standards and taxes on the new technology to support laid off workers [1]. This was rejected so they tried to protect their wage power by smashing up the machines.
A Luddite response to AI might be to tax the value AI created (Microsoft's profits) and use that to fund minimum wages/retraining. Not sure how that would work when the AI value is in one jurisdiction and job losses in another.
Tax the corporations more than the people would be a good start. Make profits from savings in manpower go back to the social programs, maybe ven universal basic income.
Banks can evaporate billions and nobody bats an eye. Zero persons responsible, zero persons to prison while the most vulnerable always pay the price for it.
> It’s unlikely that we ever move toward this, in my opinion, due to the other issues inherent to communism (unfair (from the perspective of most policy makers) distribution of resources, corruption, etc.).
It's because communism has the same issue Luddites have. Unless everyone is onboard, it doesn't work.
You can't stop people from trading between themselves for profit in a communist country without the threat of violence. This is what leads to all the other problems.
I mean Marx literally says you need to cull off the non believers for communism to work.
My own pet idea for economic reform would be to have people democratically vote on the services they want and if there aren't enough volunteers/robots/AI to perform them then you draft people. In this scenario people will get the services they themselves are willing to put in the work for. Such a system wouldn't need money, would be fair, and technological advancements would bring freedom.
> Right....and all the people not working would get paid how exactly ?
There's no money in this system.
> Or does this system just assume they're all homeless and jobless?
If people want "homes" then they democratically vote that they do and, if the vote passes, then people volunteer to build those homes. If there aren't enough volunteers to build the homes, then people are conscripted. This is not unlike the military where if there aren't enough soldiers you draft more.
Everything we have today is because someone built it. What is stopping people from continuing to build in the absence of money? It seems money is more or less a "hack" to circumvent the shortcomings of human nature. There needs to be a culture shift towards a labor-first mindset and better role models (i.e. don't glorify the wealthy, glorify those who build amazing things and share them for free). People should build and innovate because they want to, because it means a better life. In the system I've described the standard of living people have is directly tied to what they and their neighbors are willing to work for. If folks don't want to work, then we'll go back to living in caves, but if we continue pressing forward then we'll eventually enter a Star Trekien techno-utopia.
Exactly this. Advancements in technology should better peoples lives not destroy their livelihoods. We shouldn't suppress technology, but rethink the role of our economy.
Loss of income kind of understates the issue I think. I'm an already long term unemployed programmer, and I've been playing around with copilot. It makes me think I'll never have income again from that trade, and possibly no other related field.
Yeah it will ultimately lead to a better life for everyone but technological disruption has always been totally destructive to the generation it is replacing. Like the coal miners who Obama said should “learn to code”. Getting rid of coal is a huge net win but it sucks for them.
Yes! So many people in information fields think that their relatively high earnings are a result of their economic contribution. The truth, which they are often mentally unwilling to face, is that their earnings are more do to being on the profitable side of Intellectual Slavery laws (copyrights and patents).
The artificial scarcity created by these laws is what has generated such vast accumulations of wealth, not some intrinsic value to their unique creations. ChatGPT is exposing this uncomfortable truth to many people for the first time, apparently.
??? What else can we do, save for reward merit and performance? Sorry technology made the horse obsolete, but uh, that's good .. performance goes up, potential to show merit goes up
it did not, there are plenty of situations in which technology is less preferred to a horse (or mule), like say climbing everest or various other difficult terrains. it did reduce the amount of working horses though
Have you actually seen a helicopter? Know anything more than they are rotary wing aircraft? Do you know about rotor wash or range, especially when carrying a load? Do you know how difficult flying with a hanging load it is and how much stress it puts on the airframe? Did you know airframes can bend since the entire aircraft is supported by its rotor head while the airframe itself is actually carrying the weight?
Your robo horse thing also ignores the energy usage of an animal vs robot. The animal has a distinct advantage.
Again, you have no idea what you’re talking about. Hopefully you’re not an engineer by trade, as you’re failing at pros and cons here.
Interesting take — I also think these arguments come from a place where people have (subconsciously?) come to terms with doing something monotonous or repetitive to survive.
Ah yes, I'm sure you have a solution from one of the most difficult problems ever?
It's easy to condemn the system but without a solution you're just barking in the wind...
Just to be clear, I also think there are major issues with "the system", but I also don't think this is an easy problem to solve or everyone would be living in magical happy land already...
When circumstances change, people's behaviour must change. People don't like to change, some even fear change. If some people are insulated from reality, such that they don't need to change, other people will have to bare the cost. There is no economic system that can spare us from the need to adapt.
Wealth inequality in the US is already at absurd levels. The top 1% of Americans have a combined net worth of $34.2 trillion (or 30.4% of all household wealth in the U.S.), while the bottom 50% of the population holds just $2.1 trillion combined (or 1.9% of all wealth).
The Fed estimates that the wealthiest 10% of Americans hold more than 88% of all available equity in corporations and mutual fund shares (with just the top 1% controlling more than twice as much equity as the bottom 50% of all Americans combined).
Personally as a noob programmer, I feel like a superhuman because of GPT-4. Feel like my creativity has been unleashed and I can compete with the big boys.
I think that is where the scare comes from though. It used to be that churning out good code really did take a lot of experience. But as we lower that bar, the value a computer programmer has may begin to diminish. If everyone can spit out 200 lines of code in a day, thrn hiw valuable are you, really?
I analyze malware for a living, and don't consider myself a strong developer, though I can write programs, obviously. As an example, this last week I had a task that I would normally have employed one of our developers to do because they do it better and faster. Instead, I used GPT. I effectively took a couple days of work from someone. This is all fone now becuase it is new, but after a few years managers may start to evaluate output of certain people and question the utility of having duplicative skills on payroll.
To be clear, I'm not actually entirely sure this will happen. I think there was a similar discourse back in the days when excel was making the rounds because it brought "computing" to everyone-and it did. However, it wasn't catastrophic to the developer community in terms of employment.
> But as we lower that bar, the value a computer programmer has may begin to diminish.
As a developer, I feel like it's the opposite. If anything, it's going to raise the bar by replacing low skilled coders who are only good at cheaply producing piles of future tech debt, GPT4 will do that sort of work for 'free'. On the other hand it's going to empower non-programmers to write or debug low complexity scripts on their own, which is great.
I don't believe that any sort of "AI" short of AGI is going to replace developers doing "real work" on even medium complexity codebases. The reason for that is simple - GPT lacks logical reasoning capabilities. It can 'fake' them on the surface level, it might even fake them really well for extremely common problems, but as soon as you prod deeper or tack on an extra requirement or two, it starts spinning in circles indefinitely.
"Real" long-term software development is about taking (often poorly defined) requirements written in natural language, evaluating them in the scope of an existing software system, finding solutions that preserve behavior of the system (without introducing new bugs), and lastly implementing those changes in a way that follows the boundaries and abstractions defined in your system.
A single feature often touches many files at once. During this process you might spot a chance to introduce new abstractions or remove unnecessary ones. Unless you're planning on completely replacing developers with AI, the codebase must remain maintainable by mere mortals after you complete the next 50 revisions using AI that's mindlessly hacking away at your current codebase.
All of this requires logical reasoning capabilities that are, in my opinion, many orders of magnitude outside of GPT4's reach and you need those to maintain a software system for many years - decades even. That's before we get into the day to day communication and coordination effort required to sync with stakeholders, clarify requirements, and so on.
If I had to compare it to the security field, I believe that GPT will replace developers as much as automated vulnerability scanning tools have replaced pentesters. ;)
Do some more testing. Try putting it in a debug loop. Imagine tooling that has access to the files and a longer context window. If this is truly your judgement then GPT4 already has better reasoning capabilities than you. Imagine improved versions every 3-6 months.
I've done all of those things. It wasn't even operating on code but a problem described in plain English language with clear bullet points describing constraints of the problem. There were no context window limitations at play.
When it broke requirement or constraint "A", I reminded it about it. It apologized and formulated a new "solution" that broke constraint "B", when reminded about that, it apologized again and proceeded to break constraint "A" again.
The conversation went on for 20 odd turns where I tried to iterate and arrive at a solution - a custom algorithm to solve a problem it's likely never encountered before (at least in that form). It wasn't a particularly difficult problem, it just had many logical branches and steps it would have to reason about holistically. Instead it kept breaking one or more requirements that were clearly explained just 1 or 2 turns ago.
Your response is needlessly rude, perhaps the reality is that you haven't pushed it enough to discover severe limitations of GPT's logical reasoning capabilities.
> If this is truly your judgement then GPT4 already has better reasoning capabilities than you.
Wouldn't it stand to reason that someone with poor reasoning capabilities would be easily impressed by something or someone with better reasoning capabilities? ;)
"The reason for that is simple - GPT lacks logical reasoning capabilities. It can 'fake' them on the surface level, it might even fake them really well for extremely common problems, but as soon as you prod deeper or tack on an extra requirement or two, it starts spinning in circles indefinitely."
Those unqualified statements are false. GPT4 may not have been able to pass your particularly complex reasoning task, but that does not mean that it can't reason.
My tone is really out of extreme frustration because misjudgement like you are displaying literally puts the fate of the human race at risk.
Is this supposed to be some kind of joke? If someone disagrees with you, you whack them with rhetoric about existential risk? What are you? A cult member who has heard a prophecy from tech priests?
GPT-3.5 for this specific example, but I've been experimenting with GPT-4 via Bing Chat and it hasn't really changed my impression. I'm going to reevaluate once OpenAI releases ChatGPT + GPT-4 for free users.
The problem with this idea is that at some point you end up with a good approximation of AGI so humanity at large would become redundant, not just software developers.
Everyone talks about how the act of software development is being automated, nobody thinks about the impact of the software that is being developed, as if that had no impact on anyone else. Given enough effort you can replicate any human skill faster than people can retrain to an unknown skill.
I’ve personally been asking chatGPT design decisions about databases and app structure. I give it some starting ideas and ask it what would be the best path to achieve some stated goals. It gives me the options and tells me what would be the best path.
I’ve asked experienced developer friends and they say that they would likely have similar discussions among themselves. Except now chatgpt is doing that.
Right, I'm not disputing that it can be an extremely useful tool. I often use it myself to bounce ideas or to ask an open-ended questions that search engines are failing to answer, with mixed results.
My belief is that there's a huge rift between GPT-n being an extremely useful tool (which it often is) and it being able to outright replace your job.
What is the difference between me using a search engine and using a machine learning tool? The knowledge is external to me in both cases, I am just the interface between business requirements and the technology being used.
If I use an AI to use external knowledge faster then how is this supposed to threaten me? If I am a garbage scavenger and I get my resources from digging in the landfill, then wouldn't a robot that detects the valuable waste make me wealthier? I still have to pull it out myself. Ok next iteration there is a robot that can take the garbage out the land fill but not to my house. Ok next iteration is a self driving robot that can also transport the garbage to my home where I sell it. Ok next iteration the robot sells my garbage.
The real question in this situation is, does the robot cost me more than I get out of it?
You used to have to be an expert/specialist to have direct access to a computer, or understand precisely how to give them commands to work with them over an expensive connection (and on a limited basis in terms of time and how many could do it).
That scarcity wasn't a good thing. People are drastically more empowered with computing today, the barriers were dropped in a rather extreme way (compared to where it started), and that is a good thing.
These are conceptual groupings of advancement. One layer of complexity is going to be removed (broadening access), there will be further advancement and complexity where the skilled group can navigate to in order to best unleash what they're capable of.
Writing the vast majority of code isn't special or super difficult (it's time consuming and mildly difficult at worst; quite obviously there are exceptions to that). There are a million plus software developers in the US alone. It's time to add new layers of complexity and advancement. Those million software developers will have to evolve, again, myself included.
I feel the same after programming for about 25+ years. Now I get an idea, ask GPT how to do it, or if there are other options, choose and adapt to my use case.
[edit] after reading the article... Why Priya couldn't use GPT and do the job much faster?
When the colleague said s/he could do it 10x faster it was with the current GPT4 prompt limits which wouldn't exist for a "partner" company. From the last sentence we can infer that the job is outsourced, so someone "in the US" could spin up many more bots to do the task 1000s or more times faster, thus obsoleting the need to outsource the entire task at all across the whole industry, perhaps offering it instead a cheap bulk service.
And to add, many companies are going from open source back to proprietary licenses explicitly due to being unable to compete with closed companies like Amazon. Elastic, Sentry, and Docker come to mind. So any discussion of the super/inferiority of open source should include this phenomenon too.
> Open source is not an economic system in the sense in which this term is generally used.
We should move to a society where we look at software engineers as we look at road builders. City workers build roads, the people use those roads. Likewise, engineers build software, the people use said software. Our current system of (c)opywrong is bizarre and unnatural.
> "Superior" by which metric?
Well, I'm responding to your comment using an open source operating system running an open source web browser on an open source platform and you will likely read it on the same. I still use a handful of closed source products (Sublime Text comes to mind) but that's the exception, rather than the rule. This is vastly different from 25 years ago.
I'm assuming that you don't pay for a license for Sublime Text.
How do you propose that the authors of Sublime Text make a living?
Road projects are funded by the government at some level - taxes and municipal bonds. I'm not sure how that would work for software which has a potentially worldwide audience.
And do you want to run a government funded operating system and web browser?
I don't see a model where this works... unless you're thinking of toll roads as micro transactions and advertiser supported billboards while playing games.
Yes, I do pay for Sublime Text (one of the few exceptions I make and it does bother me).
I think the government should still pay for software but with the stipulation that it can only be public domain.
Governments can pay for textbooks but with the stipulation that they have to be public domain.
So contractors will bid for the work. They will do the work. Good contractors will get further work. Everyone will be able to build on the prior work done.
What do you mean by fairly distributed? If all my machines are better than you intellectually and all my machines are stronger and faster than you physically...
Then it is completely fair for me to not give you any wealth because the machines out perform you.
People fear AI because the fair outcome is in fact detrimental for a good portion of humanity.
That is the paradoxical irony. In theory to save people you must function as a welfare state with things like ubi. You must deliberately distribute income unfairly. The practical course of action goes against our moral instincts.
> In theory to save people you must function as a welfare state with things like ubi. You must deliberately distribute income unfairly.
This is only true for perverted definition of the word "fair" which allows owners/investors to perpetually capture 99.9% of the value produced by people who research, develop, build, and operate "your" machines.
When this is your ground truth, I can see how you would perceive a truly fair distribution of value created through thousands of years of collective human ingenuity, creativity, and hard work, as "unfair". Particularly in a post-singularity world where AGI and robots replace the majority of human work.
Right so if I'm a janitor and I use chemicals to clean things which is the result of hundreds of years of human ingenuity and chemical engineering I suddenly owe humanity money?
No. That is the perverted idea. I'm simply talking about fair as in fair trade. As in what is defined as a fair trade and a fair transaction according to economic theory and common sense. I am using the absolute most normal and most common sense meaning of the word "fair."
You are the one in your words: "perverting" the meaning. Perversion is actually too strong of a word. I would say you are definitely twisting the meaning and using an uncommon and sort of made up definition.
According to the most common usage of the word fair those who own AI only owe what they paid for. If they give away money then the economy is becoming more socialist or in another words an even distribution of wealth, but certainly unfair in the eyes of capitalism and fair trade and the fair exchange of goods.
Keep in mind though I'm not blindly supporting capitalism. The future of society may rely on a more practical but more unfair distribution of wealth. But we have to face the fact that such a distribution is fundamentally unfair.
"Fairness" in this definition is tied to a belief that everyone deserves a decent life.
The thought is this: we are not a society of cavemen or subsistence farmers. We're the richest society in our history by far, so all people should enjoy the fruits of such a society.
Let's say you develop a debilitating illness that robs you of your ability to produce income. Or, you have a loved one—a child—that is debilitated and will never participate in the normal "fair trade" society.
Society condemns them to a life of poverty and suffering because of their debilitation. Is that "fair" in the context of our economic surplus? If it is fair, how much more should our economic surplus be in order for these debilitated individuals to have a decent life? Will they never ever have a decent life and that's just what we decide for ourselves?
This is ultimately a moral question. Can we imagine or create a society that yields better standard of living outcomes regardless of that person's status or capability? Andrew Yang's UBI policy was essentially because he had a son with down syndrome.
If you had down syndrome, would you prefer the "fair trade" definition of fairness, or the "fair living" definition?
No. I agree that it is morally right to help people in need. But it is not a fair trade.
You cannot redefine the term "fair" to be inline with your moral values. We have different terms for what you are referring to. When you donate to a charity you use the word "donate". You have not conducted a fair transaction.
In the eyes of capitalism, it's certainly legal and to a certain degree, expected that profits accumulate at the top, but I don't believe the majority of the population ever thought of it as a "fair" arrangement.
What I'm trying to say is that your framing of the issue in terms of "fairness" isn't very productive. It may be your opinion that any given arrangement is fair, but the concept of "fairness" is really just a social construct. If your fellow citizens disagree, they are ultimately the ones who will rally to change the system. At first electorally, and failing that, through violence.
What do you mean..? the status quo is like this already. People choose the most competitive product so if a machine is the better performer then payment is made towards purchasing and maintaining a machine instead of paying a worker.
The current electorate 100 percent supports this and considers this fair. You actually have to create a new nation state if you don't want this.
> People choose the most competitive product so if a machine is the better performer then payment is made towards purchasing and maintaining a machine instead of paying a worker.
how do you explain the significant market for hand made products?
regardless, this wasn't my point
my point was the electorate aren't going to support e.g. Microsoft replacing every single worker in the US with a piece of code
regardless of Microsoft's opinion as to what it thinks is fair
>how do you explain the significant market for hand made products?
Because a segment of people think the hand made product is superior. So they purchase it. I never made the claim that machine made is superior to hand made. I made the claim that If machine made was superior then people won't employ others to make hand made things.
For a vast swath of products, machine made is often more superior. With AI, that swath becomes even larger.
>my point was the electorate aren't going to support e.g. Microsoft replacing every single worker in the US with a piece of code
The electorate is not clear about this. Morally it's a strange situation because free trade is a liberty that's part of the American Dream. If a machine can automate all jobs then it's a persons god given right to use that machine rather then pay someone to do the work. The implications of AI nor the morality of the change AI will bring is so muddy it can bring a democratic electorate into a deadlock via conflicts of interest and slow decision making.
>it's no more a god given right that it's an incited mob's right to burn down the fab or datacenter that someone else "own"s
If you change societies current outlook on morality and law then yes you are right. But currently society has laws in place that define burning down a data center as wrong. Those laws do not differentiate between whether it was done by an individual or a mob. These laws are also agreed upon by most people. You can make up your own personal morality, but good discussion should be founded on a shared reality and the status quo majority interpretation of it.
>property rights in liberal democracies will not survive a starving middle class
And this is the paradox I am referring to right? Our current interpretation of morality is at odds with practicality.
What matters is the real effects of being wealthier. If it means you and everybody else can afford a place to live, then "feeling" it's unfair just doesn't matter.
Here's an idea: a UBI that's pegged to GDP and population.
Make it comically small to start, like say 0.25% of GDP split evenly between all citizens. Based on 2021 US stats, that's $176 per person per year. That seems relatively unobjectionable regardless of your politics, even assuming that the % is likely to drift higher over time.
With increasingly advanced AI and cheap energy, GDP would rise over the long run independently of population, ultimately increasing the UBI to a livable salary.
Here is even simpler idea to make that feasible: Start actually taxing the corporations in a way that can't be trivially avoided. And don't tax them less than your own citizens. Maybe tax a bit of income on top of revenue. Maybe tax a bit more if income per employee is on high side.
If you're talking about a five-figure UBI, I don't think that would be simpler to pass through Congress.
In terms of legislative complexity, I can't see how closing all major corporate tax loopholes would be simpler than implementing whatever minor tax revenue increase is necessary to offset a $176 UBI.
Doing that is actually more complicated. There are a variety of questions regarding taxing them, and there are many more ways they could get around it. In contrast, an income tax actually collects revenue because people can't really get around having to pay it.
Well, then we have been living in a system that's as close to fair as possible since global individual wealth has been growing for a long time. The few times we had it shrink significantly over some period of time is when local populations attempted forced wealth distribution.
Our present system, by this definition, is amazing!
No it's not. If the property of fairness is that everyone grows wealthier then a system that makes everyone wealthier is a fair system. That's as close to a tautology as possible.
The resulting absurdity is why OP was right to ask what fairness was: everyone has their own belief in it, oriented towards equality or proportionality or some notion of deserving.
In order to claim that the system is “as close to fair as possible”, you would have to demonstrate that the system has optimized everyone’s wealth growth as much as possible. Something going up for a long time isn’t proof of optimization.
Well, no you don't have to optimize each person's wealth growth. It could be incredibly uneven so long as you optimize the number of people whose wealth grows.
And clearly, since it is better than every other method, it is the best by definition. If other things were not done it is because they were not possible: since possibility requires an agent to execute and since no agent succeeded in executing a better plan it is, by definition, impossible.
>And clearly, since it is better than every other method, it is the best by definition.
That isn't how "by definition" works. For that to be the case you would have to define everything to be inferior which is a purely subjective choice.
What you should have said is something along the lines of "based on our best efforts this has had the most success" which has completely different implications, such as failure to discover or adopt better systems.
It is especially strange since what you are talking about violates neoclassical models. There is no wealth inequality built into those models so why would it be obvious that this will be the best solution forever?
>. If other things were not done it is because they were not possible: since possibility requires an agent to execute and since no agent succeeded in executing a better plan it is, by definition, impossible.
Except The Wörgl Experiment succeeded in every respect. Stop rewriting history. Your theory is also unable to explain the success of the Chiemgauer [0], which is severely limited by legal problems and the ability to find loopholes.
After all, if your theory was correct and no improvement is possible, then why does improvement occur anyway? Feels like you are just taking the stance of an authoritarian thug.
[0] The Chiemgauer makes money off of ending capitalism, which is a paradox if we assume it is impossible for anything to be better than capitalism.
I was using “everyone” in the same way that I assume you were using it—everyone in aggregate. You seem to be basing this on a rather dubious position—that we’ve thought of, tried, and optimized every conceivable system for growing wealth and that the result of this exhaustive history is our current system.
You don't need to do an exhaustive search because optimality here did not account for different amounts for each. A thing is optimally fair in this world if everyone's wealth goes up. That doesn't need exhaustiveness.
A thing that gives me 1 million and you 1 is as fair as one that gives us both 500k.
And yes, we did actually search everything possible because if something did not get done it was, by definition, impossible. After all, the agent that could have made something possible could not have acted as such because we know they did not. If they could have they would have. If they could not conceive of a better thing then the thing was impossible because it was not conceivable by anyone.
Except even Fisher Black recognizes a potential currency trap at the zero lower bound and Fisher Black is someone who strongly believes in economic equilibrium.
At that point I can't help but think that most people who think capitalism works are delusional since this is such a fundamental problem with capitalism that can at best be handwaved with eternal inflation.
The US had both higher growth and higher wealth redistribution after world war 2 (extremely progressive income taxation and steep wealth taxes). The 70s ended wealth redistribution and the US has lower growth. At least get your basic history right.
Not that person, but I don’t believe that sentence approaches a definition of “fairly”. “Make everyone richer” is all fine, until you realize that you’re only a penny richer. But maybe it’s justified. That justification is what the “fairly” definition would require, and is extremely important.
The video "Wealth Inequality in America" <https://youtu.be/QPKKQnijnsM?t=35> at timestamp 0:35 shows a definition most respondents to the question agree on.
Why would anyone contribute more than is required to get what they need, if they’ll never see any benefit beyond that?
I prefer a system where people that work harder get more so they can have what they want, rather than just the bare minimum to survive (which is presumably what is meant by “what they need”).
Defined by man that have never worked honest day in his life and lived off family, repeated by people that don't know human nature well enough to know it doesn't work
Funny thing - I've been using ChatGPT as a programming assistant. My experience with it is that the more knowledgeable I am at the domain, the more useful it is.
It often generates code that won't compile or won't run correctly, but that sort of goes in the correct direction, enough that I can spot the blunders and refine my questions. Quite often I even learn a few new things when using it to explore libraries and frameworks I don't know that well but in languages that I am very comfortable with.
Now, for example, I am a lousy front end developer. Not really my area of expertise. I can do minor maintenance on an existing code base, but that's about it. ChatGPT has been more a hindrance than helpful in that particular domain, because I can't easily spot the flaws in its output, and I don't know in which directions to properly refine my questions.
I've had a similar experience (but slightly different). The biggest innovation that ChatGPT has brought to me in my programming/workflow tasks is the comfort and ease in which it creates shell scripts.
That's an area that's always been just past my comfort zone ("Create a shell script to solve this problem? Now I have two problems...").
But all of a sudden, I feel like a master at shell scripting! Things that have always been manual-and-slightly-annoying are now scripted away into automation world, and it feels like I have a newfound superpower :) This past week has been a workflow productivity superweek.
This is currently one of the biggest impacts it's had on me: I no longer fear programming languages and DSLs that I'm not completely fluent in.
I've use ChatGPT to confidently produce jq programs, and Bash, and zsh, and ffmpeg scripts, and AppleScript - all tech I've mostly avoided in the past because I hadn't climbed the learning curve far enough to be confident with them.
To me it's an extension of that great feeling when you need to do something in an area you're not as fluent in and you find an SO thread that perfectly addresses your use-case, or at least gets you 90% of the way there. But with copilot you can do it from right within your IDE, or use ChatGPT to iterate on the results.
Using it with “old” systems, like bash and objective-c, is why I decided to shell out $20/month. It easily saves me $1.25 of pain, per work day.
But, it also really highlights that it’s trained on data, and doesn’t “know”. I’ve never seen it produce a bash script/line that properly handled spaces, on its own, because most shell scripts don’t. Even ChatGpt 4.0 backed fails to “correct” the mistakes, a large portion of the time.
Shell scripting and JavaScript are strengths, any kind of server-side language like Scala or C# it really falls apart quite quickly. I think that integrating into existing APIs is the Achilles' heel, GPT-4 doesn't seem to do any better here either. It makes me wonder if someday we might not get better results completely eschewing libraries altogether and letting the transformers generate literally everything--perhaps recreating similar client libraries over and over and perhaps based on specific existing human-authored libraries, but each one unique to the service, e.g. no external dependencies at all.
I think it will be quite the opposite. Generating a lot of code means generating a lot of bugs. LMMs should get the (battle tested) libs they have to use as part of the prompt, and they should just use those APIs.
I’ve also been wondering if no framework coding will be more productive for LLM driven software.
How many times have frameworks like React changed since it was created? A changing framework means the LLM may mix training from multiple versions and create errors. Whereas libraries that don’t change can produce consistent results. So use stable libraries that choose backwards compatibility at any cost, over the ones that change with the times.
They aren’t trained on assembly. Even if they were, the tools for debugging assembly wouldn’t be as helpful if the LLM wanted to iterate when given compiler errors. The compiler errors they’re trained on are errors humans run into.
Now they also have training on frameworks but those keep changing. So I think the best abstraction is plain javascript - it has the most training data and javascript written twenty years ago still works today.
I can agree to that. I've been writing a lot small cli utilities than before, with argument parsers, help message ecc and in relatively small span of time. It is really useful and very fast.
A large time saving I’ve recently discovered is documenting functions. Paste the function in, tell it to write a docstring/whatever, and it’s 95% there, most of the time.
AI is a ratchet. It doesn't die, or retire, or change careers. Once it's good at something, it stays good. Once it gets better at something, it stays better. (If not, the model is disposed of without pity or remorse.) Right now, it may make you better at your job. But your very use of it is training it to do your job.
It seems to me that if AI is currently helpful to you, it is likely to eventually replace you. And me, and perhaps most skilled jobs as they exist today. It won't be instant, but if you are early- or mid-career, take it very seriously.
What does "take it seriously" mean? For me, taking it seriously means that I am trying to use it as multiplier to be better at my own job. Is there some better course of action you think we should be taking? I personally do not think it is going anywhere, so I figure I had better be the expert.
“Take it seriously” to me means that I’m using AI to be more productive while simultaneously preparing for a future where I can house and feed my family without relying on being employed as a knowledge worker. What exactly that looks like, I’m still not certain.
> so I figure I had better be the expert
Be an expert at what? Prompting AI to do things? There will be little to no expertise needed in the future as these tools evolve. That’s precisely what makes AI so disruptive. A basic set of instructions can be used to create something that previously would have took an entire team of skilled specialists to produce.
Sure, there will always be some experts, but these jobs will be few and far between, and they’ll be much more academic in nature. Having a job like this will be a luxury only a tiny percentage of the earths population will enjoy.
The only real question at this point is how fast will AI move to automate all of these jobs away. It could be 5 years it could be 20.
The jobs left in the wake of AI won’t require much education, skill, or talent, meaning they’ll be extremely low paying because almost anyone will be able to do them.
My problem is that without some legislation in place, there is no stoping this
In 10-20 years it will be robots with guns patrolling food production and distribution so you won’t even be able to steal a loaf of bread for your family.
I’m actually really concerned that if a more equal system doesn’t come soon. Many, many people will suffer very badly.
Treat your job like a major league sports career. You have 10 more years at most. Earn and save what you can.
I'm pretty much responding to this by trying to maximize my earning potential immediately (TC is the only king. No more gambits where I might take a lower-paying job to "learn more" or have better WLB) and planning on limiting my expenses.
IDK saving money? Make your life more about just your career like some people do? Train mental resilience? Learn a new skill? Vote better politicians who actually talk about this as a real problem?
We can all do a lot about this. Not saying it's easy though.
I think the question is, how fast can it get better? You could apply the same reasoning that you did to compilers, and some people probably lost their jobs, while others grew along with them. Compilers have been improving for a while. If AI grows as the same rate as compilers, I won't worry much. It's if/when it starts growing 10/100 times faster that things will get very serious.
Speaking about that, do you have any suggestions? I'm very early in my career, and have never experienced big transformations, huge layoff, large crisis. I guess one of the ways is regulation/unions/stuff like that, but I also don't know much about it. I'd be happy to hear how other people prepare themselves for possible industry disruption.
Every 10 years the software paradigms change so much that you practically have to start over. Some skills carry over, but many don't. LLMs will do the same thing - they will force us to change our approaches.
My friends in the gaming industry have the complains they can't get new junior and associate members on their team for development. Instead companies want to throw more tooling at them to make the senior developers more productive. With how bad companies are at providing on the job training now, what does the future look like with 100x developers versus newbies that can't talk to AI?
The gaming industry is probably the worse place to look at.
It's constantly trying to farm work abroad and looks at every possible way to cut costs. And it's dominated by young, naïve devs and artists who don't understand the market and are "passionate" about the product.
If we can get these sort of tools custom trained on proprietary custom video game engines I feel they could be enormously useful in job training and getting new jr members of the team up and running quickly.
Things like "how do I make a debug cheat command to increase player speed" would be a simple question that would send a jr programmer spending time asking around and poking through many areas of code (how do I make a debug command? oh It's imgui? how do I do that? what controls player speed?) but if an AI could provide a working example immediately that would be a huge time saver that would accelerate the new programmers' understanding of the codebase.
Or it would stunt their growth. Those sorts of tasks force you to poke around and learn, rather than having the answer handed to you by a LLM or senior engineer.
Well, I fully expect juniors in a few years to be somewhat familiar with AI assistants such as ChatGPT, much like they come with some familiarity with a programming language, an IDE, web search, etc.
I see LLM models not as the end of society, just as new powerful productivity tools.
This is because you're used to normal technological development scaling. Unfortunately with AI we are unsure at this point if our old paradigms still apply.
What happens with society really depends on where we are on the technology growth curve. If LLMs plateau for a while and we don't see significant growth in their abilities, then we'll just see pretty massive technological disruption and reshifting of human priorities, kind of like when the car or plane showed up. On the other hand, if we pop the AGI rabbit out of the top hat in short order it is going to surface deep fundamental problems that humans world wide have been ignoring because of the status quo has not demanded such rapid change.
That's because you're used to normal technological development hype. Every few years a shiny new toy enters the hype cycle, only to fall out of favor as things stop advancing as people expected.
LLMs are impressive at natural language processing (which is a damn hard problem to solve), and can both parse and generate natural language at a satisfactory level. It's an interesting facet of AI, but it also has some glaring limitations for wider use.
> Every few years a shiny new toy enters the hype cycle
I'd agree, but it's not good to forget that every few decades a new shiny toy shines so brightly that it razes two whole cities to the ground in seconds.
It's almost as if you didn't parse most of my reply.
Again, if we are close to AGI every single one of your past ideas on how technology should behave is outdated and done for.
I didn't say we were going to get AGI, and I said it's completely possible we are going plateau out. But if we create general intelligence it will be as if we have created fire, or the wheel, it will present a profound and drastic change in technological capabilities that it will reshape all of humanity.
So is a computer program that you can speak to and that determines your intent... except we actually have those now.
The real question I have is 1) how close are we to human replacement AGI levels, and 2) even if we don't get full AGI, how much of a societal shakeup is going to occur with what we have.
We are already at the point of digital development that the argument of "We dont have AGI" is mostly meaningless. We need to have discussions at a societal and legal level on what we're going to do to prepare our lives for it occurring sooner than later to avoid catastrophic consequences.
> The real question I have is 1) how close are we to human replacement AGI levels, and 2) even if we don't get full AGI, how much of a societal shakeup is going to occur with what we have.
We have been replacing humans for a long time, with animals, machines, computing, robotics and now some limited AI.
I can't answer about how much of a shakeup it will be. I fully expect the world to get worse as time passes. Enjoy things while they last.
> We are already at the point of digital development that the argument of "We dont have AGI" is mostly meaningless. We need to have discussions at a societal and legal level on what we're going to do to prepare our lives for it occurring sooner than later to avoid catastrophic consequences.
I agree with discussions on societal and legal level to reduce impact of technology on humans, but I fully expect those discussions to go nowhere and catastrophic consequences happening either way.
Literally everyone of those were massively hyped and sold as "the future"
This is not to dismiss the current trend of AI. Hell, I pay for ChatGPT premium and love to play with StableDiffusion. But I do get bored at all the LARPing about how how LLM is just a step from AI taking over the world.
None of your examples replaced humans, they were/are used by humans.
For VR, many saw through the hype due to its inconveniences and minimal benefits. If VR had tapped into our nerves then things would’ve been different. No rational person expected this.
Wearables are the future, depending on if you have any medical issues or not. You misinterpreted the hype likely because you’re not seeing the medical applications.
Crypto replaced money and banks. Anybody with an idea of the function of money in a society also saw through this one.
AI is different. It aims to replace a human brain. 5 years ago if you told me a program could listen to me literally speak and then write code that not only compiles, but works, with non trivial requirements, Id have laughed at you. Yet here we are.
Same here. It's like a well rounded but very junior level coding assistant that produces a probably flawed bit decent first pass in seconds instead of a week.
As a very senior programmer, it's the first technology in a long time that has doubled, or maybe even tripled, my productivity.
The demand for my skills is only going to accelerate because of how godly this had made me.
In the very short term maybe. But nocode tools like make.com are already very popular for non-programmers and are used by many to create custom software for their own business or department.
Existing nocode tools and other new tools such as the one I am building will incorporate LLMs and multimodal models to automatically build software. There is nothing limiting it to only be used by programmers. The systems will also have debugging loops and long term tasks etc. And every 3-6 months the models are getting better or faster. Even if that slows down we should anticipate further dramatic improvement over the course of the next two years.
It's also really good to use as a way to explore the dusty old corners of your own brain. I'm writing something in vanilla JS for reasons and it's been a while since I've written that, but I can tell pretty easily if what it generates will run/be suitable and where it needs to be tweaked.
Basically I use it as a way to induce Deja Vu. Or for things where, to quote Potter Stewart: "I'll know it when I see it."
I spent some time thinking about this when the GPTs started becoming useful, and I'm glad to see my semi-prediction come true (related toot: https://fosstodon.org/@samuelnorbury/109799880269029379). Specifically: LLMs are great when you know what to ask for, and sort of know what the answer should be - call it a boilerplate machine - but bad if you're a novice, in which case meta-analysis of a query is needed to give a useful answer to a question.
What does "novice" mean in this context? For example, I recently used chatGPT to explore file systems in the Linux kernel. I'm a novice in this field (but know Linux decently well, and the general field of file systems pretty well), but I could pretty easily tell the information it was giving me was correct.
When you don't have enough background knowledge to even verify whether the answer is plausible. Or when you don't know what question to ask.
It may very well be that newer AIs and models even manage to get that right more often, though. Or that a canny prompter will start by asking which question to subsequently ask.
As a side note, you're not a novice if you know the general field of file systems pretty well, IMHO.
> My experience with it is that the more knowledgeable I am at the domain, the more useful it is.
Exactly right. I made this argument in an unrelated thread:
I gave an example of testing ChatGPT by asking it to write CRC calculation code in ARM assembler. The code worked. It wasn’t as good as mine (slower, inefficient), yet, as you said, as a starting point, it would have been fine.
“This is today, mid 2023. Give it a year or two (maybe less?) and it will be a tool to contend with. People who like to blame everything else rather than their lack of knowledge and experience will not do very well in that world.
Why would I pay someone to do <X> when they bring nothing special to the table?
Here's the huge paradigm shift (at least for me):
I could not care less what someone knows or does not know. I care about the range and breath of their experience and how they approach learning that which you do not know.
Someone like that can use any available tool, including AI tools, to deliver value in almost any domain. Someone who blames others (tools, people, the system, whatever), cannot.
We might just be entering an era in which experience will be shown to have serious value.”
Programming languages, being precise in description and semantics, means it should be possible, for an automated system, to create new programs by unfolding and expanding already created programs to achieve new solutions. These solutions will be then be memoized and become building blocks for complex problems. A system like GPT-4 should be able to do it, sort of like generating your own training data through self-play like AlphaZero does.
That's my experience with writing text as well. If I know the area well enough that I don't really need to do a lot of fact checking that isn't off the top of my head--and I can correct any areas of nuance it doesn't get quite write--it's easy enough to get a bunch of words down on paper and rework them as needed.
I haven't found it to be a big help but it can save me time.
But if we find any web page or document that has your knowledge of what makes ARM code fast and feed that into GPT4 (up to say 80kb of assembly with short comments) along with the task then we don't need you to do that anymore.
AI in fact can use any tool, including AI tools, to deliver value in almost any domain.
So the problem with the comments here in this thread is that the obvious conclusion is that we need some kind of basic income as a floor as well as some fundamental adjustment of the system to handle the new realities of AI.
In fact due to the short-sightedness of comments like yours I am tempted to use the AI programming tool I am developing to try to build an ARM assembler expert business and sell it as Robo Martin the Master ARM Assembly Bot.
Since GPT4 can write the code for me, it is possible to launch this business within the next two days.
> In fact due to the short-sightedness of comments like yours I am tempted to use the AI programming tool I am developing to try to build an ARM assembler expert business and sell it as Robo Martin the Master ARM Assembly Bot.
First rule of having a conversation between humans: You can't have a conversation if you resort to insults.
Not only insults, but some sort of weird expression of vindictive intent? Pipe down. OK?
Evolution is what got humanity here. And, yes, evolution will produce AI that will be far more capable than us at many levels and across a wide range of domains. That is inevitable.
However, there will be boundaries for quite some time. Areas where AI will have trouble inserting itself into. Don't ask me what these areas might be. I have some ideas and thoughts on this, yet, I don't really know. In other words, I feel like that conversation would be pointless...just like trying to predict the future.
There might also be lots of areas where AI will not be trusted for a range of reasons.
As a general statement, I will still hold to the belief that one of the key differentiators as AI becomes more widely useful will be the experience and knowledge of the humans wielding it. We might also see an advantage in the realm of creativity. Today? Absolutely. Ten years from now? Don't know.
Can someone create a better ARM assembler writer, one that might beat most experienced programmers across a range of criteria? Sure. Of course. These are mechanical things in the end. There are books, tons of them, written about how to write better code in assembler. If someone did, it better not be a commercial enterprise, making money from writing assembler code isn't likely to be a thing, particularly when one can already do a decent job of it for free.
My prediction is that the divide will have experienced and widely knowledgeable people on one side and everyone else on the other. Part of engineering is knowing what questions to ask, when to ask them and when they might be relevant. This becomes particularly complex the more multidisciplinary a project might be. This is where, for now, experience wins.
I've been challenging everyone that LARPs about the capabilities of GPT to start a business now, and use it in place of developers. Hell, for a $20 account you get the perfect developer, that is extremely productive, never gets tired, never gets sick, and has no PTO.
By this logic, Priya (the subject of the authors post) would not loose her job but rather just become more productive at her job. And I think that's the key to this whole "GPT4 is taking our jobs argument" that people need to understand, GPT is a bit like Autopilot in a Tesla, it can do the work for you but you still need a trained person there to guide it.
Folks like Priya will not loose their jobs IMO, the company would still need them to provide that last line of validation on data because you just can't blindly trust GPT (I don't know if we will ever be able to bindly trust it), rather the scenario I see is that their team at work would actually be able to stay on top of their assignments instead of constantly being overworked.
With GPT-4, Priya can do the work of 10 data curators in the same amount of time! She won't lose her job, they can afford to pay her more, because they won't need to pay 9 of her colleagues. Unless of course, one of her more experienced, connected, upper caste colleagues gets the 10x job instead.
Today you need a trained person to guide it. However I’m not convinced that will remain true in the future.
The validation of work is interesting. It does seem essential but it also occurs to me that this would be an absolutely horrible and tedious job. I wonder who would actually be interested in, for example, spending 8 hours a day code reviewing a an AI’s output?
He knows she will lose her job because he literally said they don't need her anymore since he verified that he can do it with GPT4.
And the new FSD in Tesla only requires people to supervise closely mainly to avoid getting sued. If that system made a lot of severe errors then it would not be deployed.
We have working self-driving in Cruise and Waymo. The only reason to think we really need humans driving at this point is denial. Actually if we switched to AI drivers entirely with the existing systems that would make the roads vastly safer. Accounting for the most erratic behavior of human drivers is one of the biggest challenges.
We're also seeing with the AutoGPT/BabyAGI type apps that while there is an exciting initial demo, GPT-4 is not ready to just autonomously develop any high quality complex app by itself, soup to nuts. This status quo might not last more than a few more years, though.
Since you are actually using it to write code I have a question. Would it be fair to characterize its programming ability as "writing imperative code" or say creating macros and glue code? Or can it do higher level stuff like choosing data structures and algorithms?
It's important to understand that it doesn't know anything. It gives approximate answers based on statistical relevance.
For example, it has been noticed that ChatGPT can answer leetcode interview questions. That doesn't surprise me in the least, chances are that it contained the algorithm associated to slight variations of the question in its training data.
To generate boilerplate code it has been pretty good. Those are pretty repetitive tasks, so it is also expected.
Using it to explore the capabilities of frameworks, libraries and services has been great for the most part, but it sometimes tells me things that don't exist or just plain doesn't work. The funniest one was when it told me I could use an annotation on a method to do something, but the annotation didn't exist. When I highlighted it to ChatGPT, it started to get in a loop with variations of code that didn't work, claiming the previous answer was valid for version 3.0. The library doesn't have a version 3.0. it doesn't even have a 2.0.
Getting it to code is a wild ride. Sometimes it gets real close to give me something workable, sometimes it gives me stuff that will never work.
However, it is awesome at telling me what code is doing when I paste a snippet.
This exactly. I've been using it to write R code because I've never learned R and needed to quickly write a lot of it. This kind of worked because when I get stuck on a bug that I can't figure out that was generated by chatgpt then my colleague helps me. But really this leaves me with questions like, what if it didn't make so many bugs? What is there was an interface that just evaluated the code I asked it to write? What if most code writing jobs become prompt engineering jobs? I agree the more expert I am the better expert chatgpt seems to be. It will never know what question I am thinking. But it does seem to accelerate or replace a lot of human effort.
It's not bad for something that's pretty new. Now imagine what another decade or two of development will give us. The number of areas in which a typical worker is more knowledgeable is going to get lower and lower.
Exactly. Every discussion I see focuses almost exclusively on AI as it exists right now. Everyone is either dismissing the impact due to some minor shortcoming, or wildly overestimating the short-term impact. The one consistent thing among those who dismiss it and those who think it's going to change everything in the next six months is that they're both drastically underestimating the long-term impact. GPT is already behaving in ways that researchers did not anticipate.
Two decades? It added 40 IQ points in the last six months.
It can already ingest 80kb of information instantly and use it to perform any knowledge task that can be described in that amount of info (with the 32k token model).
The number of areas in which the typical worker is better than a GPT3.5 or GPT4 system that has been properly integrated with the correct data and tools is already probably less than 5% for knowledge workers.
I was thinking specifically of all the amazing work that has been done since the Attention is All You Need paper from 2018. There’s been a lot of progress in just the past 5 years.
Note that you are using today's version? How much better will it be in 5 years? What if it is coupled with system who understand the programming languages so you don't get code that doesn't compile anymore?
But on the contrary, It can speed up learning a technology as you go, like a senior engineer packed with knowledge available to you. You could be not knowing the frontend!? You can ask it exactly what you don't understood.And it'll never get bore and try to formulate the answer in a frame that it settles you an understanding, not limited to what your senior has settled with. I would say, it's a good tool available to you when senior engineer/mentor isn't.
This article is not about ChatGPT, but GPT-4. I've found the latter to be significantly better at being a coding assistant in all areas: the code actually compiles and often works out of the box. Even better than chat, I can paste it's generated code and simply respond with any errors given and it will fix it accordingly, something I had lots of trouble using chat to do. GPT-4 is that much better and it makes sense to me that the author is lamenting now and not 4 months ago.
For coding, at least for me, it's marginally better than 3.5. In fact, I sometimes prefer reverting back to 3.5 to get speedier output.
I am finding ChatGPT-4 much better for other tasks that have less strictness requirements. Such as parsing through a large text and summarizing it for me, and for creative tasks.
So if you have to babysit it anyway (which is actually a correct way of using it, instead of getting fooled into assuming it's an expert: Use ChatGPT for brainstorming, have a human in the loop to validate): Wouldn't it be faster to write the code yourself?
And if you have to come up with the code yourself, wouldn't that allow you to come up with a better architecture for your whole project?
In that sense it is not different than any other powertool. A handheld circular saw in the hands of a good craftsman is a serious time saver and will help the make more accurate work. In the hands of an beginner it will lead to bloodshed. In the hands of an amateur it will produce faster work but probably not as accurate.
The big oversight here is that Priya does not want a job, what Priya wants is an income. The point of life is not working, the point of life is to enjoy it. We should strive to eliminate as many jobs as we possibly can, the less we have to work the better it is.
To make this possible we need to find a way to a new system that doesn't directly link labour with income.
What a profoundly naive opinion. Most people find meaning, fulfillment, even contentment in working, especially when the problems are engaging and the solutions produce value. Many people claim their lives would be better if they never had to work, but they are bullshitting themselves with childhood naivete. Not working is a sucking void of boredom, nihilism, hedonism, and despair. I've been through some of that before. We humans are not built for it. We need something valuable to do and most are incapable of summoning valuable ideas and tasks from the ether.
"Work" above is being used in a more specific form than you are using it. GP is not referring to all productive work, they are specifically referring to employment on the market. Yes, human beings are better in relationships and better when they help each other, but GP is not talking about abolishing helping other people or doing meaningful things.
There are a huge number of things people can do to meaningfully make the world a better place outside of traditional jobs. And a non-trivial number of people work at jobs that aren't aligned with producing value or helping people in the first place.
Value on the market in specific is not the be-all end-all measure of whether work can be personally fulfilling and validating. A market job can be meaningful, yes. But it's not the entire category. If I never had to work for income I would still "work", but what I worked on would be very different and would probably focus a lot more on non-scalable non-commercial smaller projects and volunteering.
There are things that are valuable and meaningful to do that don't involve working specifically for a company and don't involve looking at that work primarily through the lens of "how can I make money off of this?"
I generally agree with you in principle, but it’s not a given that you can find meaning outside of the job market if the market doesn’t find your labor valuable.
What if nobody actually wants your “help”? What if your labor is not only worthless in the job market, but also in general, where people prefer assistance from AI instead of from a live human person? What if no matter what you do, some AI does it better? How will humanity find our own value and meaning when that happens?
I think the point where that is the case is pretty far off, since it requires endless fully-autonomous robots and no demand for human-created media or connection.
But regardless, people throughout history have found happiness and meaning in their life completely separately from what they did to put food on the table.
That would really only be a problem if majority decided to not do anything and we had actual shortage, not just "corporations don't want to pay decent wage so they can't find people"
If the incentive is "here is basic income, you can afford flat on outskirts of the town or in some small town and basic necessities", there is still plenty motivation to do better and get better stuff (whether just for living, or for your hoobbies or interest), just not a pressure of taking first job you can find just to afford being alive.
So average person have option of just going on 6 month hiatus to learn some life skill, or artist have time to develop their skill enough to make art or music that gets enough interest to make it into income.
I don't think this is something people should be worried about. There is so much stuff to do in the world, and quite frankly, there are not enough people to do all of it. And a lot of that stuff is not particularly suited to AI.
But what I would question if you want to get a little existential -- do people value being helpful or do they value feeling helpful, because those are two different things. And I think that if the idea of "people need help and what if an AI can help them better than I can" is actually terrifying to people, that should maybe prompt a small amount of reflection about our motivations for helping others.
But the shorter answer is that there is just so much stuff to do in the world right now.
I'm so disappointed in the other replies to this comment.
> Don't worry about it, there's a lot of stuff that needs to be done
> pretty far off
> chess grandmasters are ok
We are on an exponential curve of being able to create agents on demand that can essentially act in human ways, at least digitally/online. If you're working on a computer (aka all white collar jobs or anything that can be done remotely), it will soon enough be trivial to create an agent and task it with "Unqueue tasks from the backlog and implement fixes in the codebase. Ask questions if you need help." and it will do it. And you can create as many of these agents as you like.
As many as you like! On demand! How the hell are humans supposed to compete with that?
I mean, that isn't a "what ever will happen to my job?" level of concern, that's more "will society handle transitioning to a post-job reality once everyone is useless without revolving into a war" or "maybe humanity will cease to be relevant and we'll all get killed by the computer we design", which is a fundamentally different level of problem, right? Like, the last thing I am going to be concerned about is my silly job in the future you are positing where all white collar jobs are replaced, as to be quite frank about it: my job as a low-level software developer is harder to replace than the jobs of the people who hired me or the people who hired them or the people who invested in their company to begin with... once the computer flips from the regime of being worse than a human and yet helpful to them into a theoretical one where it is better than a human, I think the answer is going to very rapidly change from "maybe you should just consider it to be helpful!" to "maybe that will be the end of human civilization" with very very little in between.
The professional chess community has been living in this world for a long time. The engines crush us, and their games can be fascinating too but Magnus’s and Hikaru’s make a helluva lot more money. It’s not a winner take all market in general but the human element is actually very important; the creation is more than just the game on the board.
> it’s not a given that you can find meaning outside of the job market
That's bleak af, how old are you ? where do you live ? what do you do ? do you have a family ? do you have friends ? hobbies ?
I can guarantee you the vast majority of min wage workers would absolutely find a meaning in things other than flipping burgers or triaging the shit people buy on Amazon
I think there are 3 factions in a world where AI took out most jobs (with UBI of course):
#1 There will always be jobs requiring humans - jobs that require human interaction. The supply will be much smaller, but so will be the demand.
#2 By the time AI replaces all jobs, we will most likely have a very realistic VR with multiplayer capabilities. I think that many people will live adventures in such world and spend most of their waking hours in it. Metaverse sucks but it's only because it's so artificial. If you could have tech that could integrate with your senses directly, giving experiences on par with the sharpest lucid dream... that's going to be much different and for better or worse, a lot of people will get sucked into it. Of course, it's going suck - life is about yin-yang, endless pleasure is not good. People who will end up spending the majority of their time in such VR will not be unlike drug addicts, unless they will also be doing activities that require mental & "physical" engagement (I think one of the coolest thing that could arise out of it are new sports that would not be possible in the real world), however, that yin-yang balance would be hard to achieve when there's no evolutionary pressure combined with overabundance of simple pleasure that's just available all the time.
#3 Walking the path to mastery in some pursuit - i.e. artistic, athletic, a craft. There's pure joy in just getting better at something and enjoying every day of practice and most importantly - feeling challenged which is a primal need. It may be competitive as heck to get some recognition or play in the big leagues (which would be more like #1), but that would be just a bonus from that perspective.
If AI leaves us nothing to do, then #3 will always be available. AI will not take away our own engagement but engagement requires effort and so, I would bet that a significant majority will overindulge in #2 to their unconscious doom - I guess it will still be a pretty cool experience though and it's not like those people will not have a choice to get out.
I your work is not producing anything valuable for other people it's void and you will get bored pretty fast, it's a human nature. If it does you can always find a way to monetize it as people need it and ready to share their wealth for something they need. No, it doesn't have to be a work "for a company", but if you can't "make money off of this" it probably means your "work" is only relevant to you, or somebody else will "make money off of this" using what you have created. It's how society works, and we are social animals.
> I your work is not producing anything valuable for other people it's void and you will get bored pretty fast, it's a human nature
I think this is plain wrong. There are plenty of pursuits that are “work” on the mental or physical side, but do not produce economic value. Developing artistry by mastering a medium or an instrument, climbing mountains, running ultra marathons, tending to a garden or bonsai, modifying a vehicle… These are things could produce economic or social credit, but are largely solo “work” which can be (and often is) self satisfying without external motivation.
People are very attached to the idea that humans don't want to master things unless they're the best at them, and I feel like that philosophy was pretty solidly disproved right about the time that video games were invented. People master skills in non-competitive, solo settings.
Learning a skill can be inherently satisfying on its own. Personal development is satisfying regardless of where the people around you are. Or at least, it should be.
And it's also kind of a bad approach to value as well -- what I've found is that you can actually be pretty average at things and still provide a lot of value to the people around you, because of ignoring economies of scale and because of how much stuff there is to do in the world to begin with.
There are software niches that are underserved where genuinely earnest programmers who look to help could do tremendous good even if they're kind of average/bad programmers. In fact, as one example that's close to HN, that's how the majority of Open Source programming happens. Open Source is not a meritocracy, it's a Do-ocracy, and a ton of the most valuable stuff is built by average programmers who look at underserved niches and say, "but what if there was a non-predatory solution for them?"
A lot of what makes a good Open Source solution is just that it was built by someone who cares and who isn't trying to maneuver you into a predatory relationship. And sometimes it turns out that there are only a few people available in a niche that have both the resources to do that and the inclination. So they're not competing with anyone, they're just the people who happened to be available and willing to do the work.
I didn't say "economic value". Let's take "modifying a vehicle" as an example. Will you keep it in your garage guarding it from anybody's sight? Why are you doing it? What's coming to your mind? It's not always as straightforward as "economic value". You want somebody to look at your vehicle, you want to show it to somebody. What for? Keep it in your garage, you are doing it for your "mental side", aren't you? Money and economic value is not the only way of keeping society together, there are others. If you are showing your vehicle to somebody, you _are_ expecting something in return. Acquaintance? Friendship? Help when you need it? Continue yourself.
This is kind of a circular definition. When you get this broad with your definition of value/payment, basically what you're saying is that work is meaningful if you derive meaning and/or personal value from it. Which, sure, I agree with that.
But that doesn't mean it'll be monetizable in the traditional sense, and it doesn't mean that traditional employment is the only place to get that value. Many of the things you're talking about aren't representable in dollar form, and it's not clear to me how decoupling income from traditional jobs would mean that those activities would stop being meaningful. Certainly, a lot of those activities are already activities that you can't really make money off of (or at least the vast majority of people engaged in those activities can't).
I specifically mentioned that you don't have to work "for a company". Jeff Bezos is not a traditional employee last time I checked. Neither are mom and pop shops or self-employed contractors. Just not everybody wants to deal with a hassle of being the one. But aside from that a lot of "no money" activities bring you friends (AKA connections), position in a society (think about OSS, can it help you to find a good paying and interesting job if you are Linus Torvalds?). Sometimes you get benefits where you don't expect. It's still "monetizable" in my books as opposed to "I'm doing something nobody needs and enjoying it while living on a basic income".
I think that's completely reasonable to have as a definition, I've got no issues with you there. I don't think it contradicts anything in the above thread though.
The "monetizable" activities you're talking about here under your definition will still exist in a theoretical world where AI takes over traditional employment. Separating "making a living" from "having a traditional job" wouldn't get rid of any of the social monetization you describe.
AI won't take over traditional employment either, humans tend to congregate and choose leader(s) as many tasks are not possible to accomplish alone, with AI or not. If there are leaders, there will be an employment of some kind, it's a fundamental thing. Money is only an equivalent of a value in exchange, so "monetizable" in the wide sense of this word is "exchangeable", and it almost always applies to social activities even like running a marathon, otherwise people would run those 26 miles alone in the forest.
> otherwise people would run those 26 miles alone in the forest.
This is kind of a side note, but have you never learned an ability or tried to master a skill in secret? There's nothing wrong with being motivated by social capital, but if you extrapolate out from that to assume everyone is primarily motivated that way, you might be universalizing a personal trait that isn't really universal.
There are a lot of things I practice and do alone that never get exchanged for social capital: drawing, I play single-player games, I cook. These are activities where I either master a skill on my own (sometimes purely for the intrinsic motivation of mastering it even though it produces no value outside of that), or because (in the case of things like food/personal-programming/etc) because it produces "value" for myself that isn't exchanged with anyone else.
I'm not saying community and social capital doesn't exist, but if you are defining value purely in a transactional sense, you are missing out on a lot of human motivation. People do things alone without ever entering into a community around those activities or showing the results to anyone else.
> People do things alone without ever entering into a community around those activities or showing the results to anyone else.
Of course! I'm not saying that "everything is for sale" or we always need to contribute to a society. But if you don't do it you may quickly find that your life is boring and you need to share with somebody. Obviously all people are different, some need (or can bear) more solitude, some hate it, but on average we are social animals and it's inside us. Even when you cook for yourself, aren't you ever discussing it with somebody? Hell, why am I typing all this? It has no transactional value for me, none whatsoever, in fact I wasted half of my Saturday :) I could have just created my theories in secret and enjoyed them, but for some reason I need to post here. Maybe because I want to know what other people think, what if I'm dead wrong with my theories? So there is a transactional value even in these posts as I learn something new which may help me later :) No, "later" is not a conscious reason why I'm doing it, it's a subconscious thing, our internal program.
> Even when you cook for yourself, aren't you ever discussing it with somebody?
Very rarely? I cook so that I can make food that tastes better to me, because I'm eating it. If every other human being on the planet was dead, I would still be doing it.
Humans are absolutely social animals, but we're not only social animals, and I think it's a mistake to try and compress every human motivation into how it benefits social interactions. Even in larger tasks, there is something intrinsically kind of satisfying about doing something for yourself even if it's fully private. Genuinely, I don't know how to explain the inherent pleasure of researching a useless topic or getting lost in an activity/task that's not going to be shared. I don't think that's something that can be reduced to "well, maybe you subconsciously think it will help you in a future transaction."
I'm getting value out of cooking, sure, but that value isn't really something that can be described in a transactional form or even as prep for future transactions or competitions. Cooking doesn't make me better in other social situations. It doesn't really give me transferable skills. I don't really cook for other people (my tastes are very different from them and I usually doubt they'd like what I cook anyway). I'm not trying to make myself more attractive to other people, I'm not prepping myself for a future competition. I don't think that cooking is going to be suddenly useful in the future in a social situation.
I just want the food to taste good because I eat it.
I think with any of these activities you're talking about, ask yourself, "would someone still do this if every other human being on the planet was dead?" And if the answer with any of those meaningful activities is 'yes', then that suggests that for some people there's something deeper or more instinctual going on there beyond just a subconscious adherence to social systems. There's a lot of stuff that I do that I would still do even if I was never going to interact with another human being for the rest of my life.
I can't speak for anyone else, but that may be more common than you realize? You can define value however you want, but I do think that you're going to subtly miss out on intrinsic motivations if you try to fit all of them into an extrinsic lens. You can theorize that people anonymously donate to charities or build useful things always because there is some kind of transaction at play there or preparation for a future transaction (and some people are motivated mostly by that stuff, which is fine), but universalizing that is not going to give you a good predictive model for how everyone is going to act in the future.
> If it does you can always find a way to monetize it as people need it and ready to share their wealth for something they need
I disagree with this entirely. If this was true, the main question we would ask in a business is whether or not the output was useful. We don't ask that, we ask if it's "sustainable", "profitable", etc... We ask what the moat is around it.
There are many useful things you can do that you won't be able to make money off of. I don't think it's uncommon either. Business is a great way of extracting value, I like business as a value extractor. But it's a specific way of extracting value. There are lots of things that are valuable that don't happen because it's not clear how they would be profitable.
I mean, the simplest example here is you can build things for people who don't have money. It's not the only example, but it's a pretty obvious one. And you are not going to make a lot of money doing that unless you build a predatory or exploitative business.
> or somebody else will "make money off of this" using what you have created
I will also point out that if other people making money off of the things you do is a turn-off, it's not clear to me what value you think you're creating. I would argue that "meaningful work" very often benefits other people, that's... that's the point. If you're not giving people more value than you're taking from them, you probably aren't doing useful work. Are you arguing that it's less valuable if people are extracting extra value from the things we do?
Let's start from basics. People need to eat, so somebody needs to make food. Those people need tools. Somebody needs to make tools. Now for this to work they need to make extra food and exchange it for tools. This exchange has been in development since before human existed (look at wolves pack) -- never perfect, but kind of worked. So you want to make something you like and nobody needs? No problem, go for it. Where are you supposed to get food? Do you want a government to pay you the basic income? That means those who make food will give it to you for free, which means they won't get tools, which in turn means they won't be able to make that food. Oops. In a balanced system you are never "taking more than giving" or vice versa, because, as you know, price is a result of supply/demand. How do you know you Java library is worth a breakfast?
I'm not sure this has anything to do with the original comment or point I was trying to make.
That being said:
> In a balanced system you are never "taking more than giving" or vice versa, because, as you know, price is a result of supply/demand.
Literally all of economic development and growth is predicated on the idea that this is not true. If work was actually zero-sum and all of the transactions gave you the exact value that you sold, there would be no point in forming a society around this.
Society works because combined labor produces more value than is put into the process. That has always been the case. You get more food out of farming than you put into it, otherwise it wouldn't be worthwhile to farm.
> That means those who make food will give it to you for free, which means they won't get tools, which in turn means they won't be able to make that food.
Also, the only reason we're having this conversation is because the "tools" that are being made will (very theoretically) be made for practically free by AI.
We're not talking about a world where the tools stop existing. This entire conversation started with someone asking "but what if there's no more need for humans to make the tools?"
> You are talking about added value and it's beyond "basics" :)
I don't know, I think it's pretty important to a conversation about automating jobs that we not treat jobs as if they're an optimized equivalent exchange. The whole premise there is that the machines are going to start producing a lot of value without any human input. If it happens, it's not going to be equivalent exchange.
If we're not talking about added value, then there's nothing to worry about because then the machines can't automate the jobs, because that would be added value.
> if your work has no value, there is no breakfast to exchange it for
My point more specifically here is that there's a lot of value in the world that can't be exchanged for breakfast, something that (as far as I can tell from your other comments on this thread) you actually agree with, right? There's value that exists outside of traditionally monetarily compensated jobs.
In a (again, entirely theoretical) world where AI gets rid of the need to earn your breakfast, that doesn't mean there's not going to be anything of value to do anymore and that everyone's life is going to be meaningless.
Machines don't produce a value, humans do. Simply because the "value" (added or not) has a meaning only when you exchange goods or services. Nail gun makes things much faster but it's a carpenter who produces the value.
Money is simply a universal equivalent of that value, nothing more. So if you give me a breakfast for help with unloading your truck, it's still an exchange, and my work's value is equal to "one breakfast" even no money was involved.
AI is just a nail gun, there still needs to be somebody who trains/operates it (like with ChatGPT) and who will ask for something in exchange. It may eliminate some jobs (happened before), but it will create others because human society is not only about food (not sure ChatGPT can help here though), but about interactions which are not going to be automated by ChatGPT (think of sex, power).
> Simply because the "value" (added or not) has a meaning only when you exchange goods or services.
I feel like your definition of value is jumping around quite a bit. In another comment you described "value" as essentially any kind of social capital or personal reward. Now it's explicitly transactional?
In any case, this is a very narrow definition of value that I don't think matches up with what most people who worry about automation are talking about. It's certainly not what the original thread was talking about when it worried about people without jobs not being able to find meaning in work. What most people think of as useful or meaningful purpose in their lives does not strictly map to transactional value.
> AI is just a nail gun, there still needs to be somebody who trains/operates it (like with ChatGPT) and who will ask for something in exchange.
Then there is no problem! This isn't an issue if AI isn't going to take jobs away.
People on top of the company don't make anything but earn more than anyone that does, Not like 2x more or 5x more but 10-1000x more. There is no person on earth that produces million of value a month in actual improvement of society, aside maybe a world leader that stops a wary from happening. Not a man in widget company making beepy boxes that spends time on meetings about barely related to that. And then neither them or corporation gets taxes nowhere close to what the normal employee is, so the corporate wealth doesn't even benefit the country it is in.
The whole problem is that any improvement in production is only tangentially passed to society and mostly exploited to make few wealthy
> And then neither them or corporation gets taxes nowhere close to what the normal employee is
How did you figure that? Corporate tax rate in the US is 21% which is roughly equivalent to an effective tax for a single filer with about $180K in income. Can't say we are talking about "normal employee" here. Besides if you are talking about dividends (which are distributed _after_ 21%), there is a dividend tax on top of that, which, depending on your share class, can be the same as a normal tax rate. So yeah, nowhere close, usually +21% for the preferred stock.
Also don't fall to that communist idea. I grew up in the USSR where we had a "fair" distribution (no, it wasn't fair) -- trust me, you don't want to live in that world. There were some upsides, but still, and it didn't end up well.
>If this was true, the main question we would ask in a business is whether or not the output was useful. We don't ask that, we ask if it's "sustainable", "profitable", etc...
To be fair, we do ask that: if you have no revenue, then you don't have a business, because the output is not useful. An output can be both useful and not sustainable. Giving away $100 to everyone that high fives you is not sustainable, for example, even though it's very useful to the recipient. It's certainly not profitable.
> if you have no revenue, then you don't have a business, because the output is not useful.
I'm having some trouble reconciling this with the rest of your comment. You go on to describe an output (giving money away) that is useful but provides no revenue.
I would agree that a useless product will very often have a hard time generating revenue, but I would not say that a lack of revenue is a strong signal that an organization is not producing useful output. I mean, the software industry is filled with examples of projects that are wildly useful to everyone but are perpetually underfunded and produce very little money for the people working on them.
I would definitely agree with the truism that "if you have no revenue then you don't have a business", but it's just not clear to me where the "because the output is not useful" addition to that truism is coming from.
People who have earned enough wealth to not for a living do, though those who've worked hard enough to do that typically don't have much in their life but work.
People who simply have enough wealth to not have to work are on a hedonistic treadmill most of the time
You think so? Have you been in that position? I was. It's not what you think it is. Also unless you want to spend your wealth pretty fast (money has a half-life time like radioactive elements, doesn't depend on quantity) you have to work to keep your wealth, and it's not less nerve-racking than spending your 8 hours at work and forgetting it until next morning.
No, I haven't been, just know some people who are.
I don't understand what you're referring to. Where was your money going? I understand you still have expenses when you aren't working, but the expenses don't scale up on their own.
Hobbies aren't necessarily only relevant to oneself, so no, they don't fit. Running a marathon can be a hobby, and lots of people compete in those together.
Not necessarily, but more often so than not. Even the competitions that you mention are only valuable to other hobbyists, and only in so far people's free times allow. Non-hobbyists are not likely to pay much to see those competitions. And when free time runs out, those hobbies are amongst the first things to go.
Someone has to grow, process, and ship your food. Mine the coal, or build and maintain the energy infrastructure. And roads. They expect to be paid because in many cases its work more than keeping busy. Those things that are more valuable or meaningful are valuable and meaningful to you, so not really a fair trade to the people doing work to support you.
I want to be polite about this, but I hate how I can correct one specific point on HN, and then I instantly need to defend an entire philosophy.
The comment I was replying to argued that we were talking about abolishing all meaningful human activity, and I pointed out that "meaningful human activity" and "gainful economic employment" are not the exact same category.
I don't really think that warrants having an extended debate about whether or not decoupling income from "work" is fair or not. And it's kind of a weird sequitur anyway, because all of the jobs you're talking about are paid noticeably less than white-collar jobs even though they are arguably way more essential than any of the programming work that we do. So for this to suddenly be a conversation about fairness... I mean, what conversation do you want to have, do you want to have a conversation about AI or about the entire history of wages and about how human beings value blue-collar jobs?
It's not a problem, it's just... people read way too much into comments like this. I'm just pointing out that "meaningful work" can happen outside of an economy, something that I think is a pretty obvious, uncontroversial point to state.
I think your response is equally naive. I am still largely undecided on whether something like a universal basic income would actually be a net positive for society, but the fallacy that receiving a fixed income immediately means that people won't do something productive with their time is ridiculous. I can't imagine _not_ working, I develop open source software in my free time and I would spend more time producing software others find value in if I spent less time working for my livelihood.
This doesn't just apply to software development. There are a lot of garbage jobs, dead end positions, where the people are effectively not doing anything. That is a weight on our economy but we can't just cut them out. What would those people do if they didn't have to waste so much of their time to live? Sure there are going to be people that go all in on becoming puddles on the couch, but I'd argue more people have passions they would actually have the energy to pursue.
People could spend more time with their families without being stressed out and burned out by everything else in the world. I'd argue that would most likely lead to healthier childhoods for kids, likely with better supplemental education as well leading to a smarter society in the long run.
People get tired of partying, and the people that don't make good examples for the next generation of what not to do. You can see that in our current society as the younger generation is drinking significantly less and doing fewer drugs to the point major alcohol manufacturers are concerned about their bottom lines.
There will always be degenerates, but people want the fulfillment that comes with actually doing things like you said. They will find that one way or another.
What do you consider as "productive"? Look at animals in a zoo, do they look productive to you? They have "a universal basic income", they simply don't need to be productive. Humans, just like animals, are productive when they are trying to achieve something (catch food, find mates, and for social animals to establish their position in a society which leads to food, mates etc.). E.g. you are developing OSS -- ask yourself why? Forget about money for a second. Are you doing it for yourself only, just for a pure fun of manipulating characters? Or you expect your software to be used by others? Revered by others? So if it's useful for others do you expect them to use it for free and pay you through taxes via the universal basic income (relying on a government to do a "fair" distribution), or maybe just pay you directly thus showing that very reverence? So it's just a distribution problem. If you don't want to worry about selling your software, then let others do it (it's called "working for a company"). As opposed to a government, which can pay for a work not needed for anybody (not very efficient, but that's what governments do all the time). Want to spend more time with your family? Don't buy the latest iPhone or an expensive car and work remotely part time, you will be able to spend more time with your family. There are tons of possibilities. Yet people do want the latest iPhone and then complain they don't have time to spend with their family or do "what the like".
So is all of humanity, we call them jobs and debt. Almost all of those animals lives would be considered luxury by human standards. No worries about food, a safe place to sleep, or predators.
A lot of people have to work two jobs just to afford food and shelter. Granted there are also people trying to live a Champaign lifestyle on a lemonade budget, but how do you address the first group?
This world is not fair, do you know how to fix it? I don't. There are different models with different degrees of fairness, but all have their downsides.
You not being able to imagine it only means your imagination doesn't go far enough. I have personally had experience with people who in fact would rather live off their parents' wealth in a hedonistic manner rather than working. One person hasn't finished his studies after 10 years and still spends his days traveling world wide first class using his parents' allowance. These are not isolated cases, they are common amongst a certain population subgroup.
My hypothesis is your drive to work is a product of your education and environmental conditions. When education and environmental conditions are different, you may not have that drive.
It isn't about productivity by itself. It is about aligning production with consumption. It is wildly naive of Westerners to believe there is so much excess production in the world that we can just pay people to not work. The US got their "UBI" in 2020, and it was Americans sitting around while foreigners labored in factories, docks, and ships to produce and deliver the consumed products.
Yes, there is a tremendous amount of waste in the global economy, but if we want to improve quality of life then we should focus on the mechanisms which cause that waste in the first place (e.g. targeting GDP growth.) If we solved those excesses (a very tall order), then why would it be fair for one group to be over-consume at the cost of another groups over-production?
Lockdowns were already a test of exactly what you're saying here.
When almost no one had to work economics became ridiculous, people were paying $40 for a $15 meal to be delivered to them, fiscal policy became clinically insane, tech stocks minted a new bubble. Are you proposing that bubble should be more permanent? The real economics of 'figure it out or lose your lunch' is much better policing than 'figure it out or go back to UBI'.
Burning an entire generation so the next one will be better isn't good policy.
> What a profoundly naive opinion. Most people find meaning, fulfillment, even contentment in working [...]
Agreed. I just spent a week volunteering. (At the Pinball Hall of Fame in Las Vegas, repairing machines.) It actually cost me money to do, but it was incredibly satisfying to just go and do a concrete thing that made the world better and was immediately beneficial to people. Especially in the company of other good people doing the same.
But I think a lot of people have had only terrible jobs (valuable work in inhumane conditions) or bullshit jobs (meaningless work in whatever conditions), so I get how so many people have been conditioned out of seeing the personal, emotional, very human value in work.
No. I also like jobs. I like them better, as they're cash-positive. I haven't liked all my jobs, but that's because some of them were terrible or bullshit.
> Most people find meaning, fulfillment, even contentment in working, especially when the problems are engaging and the solutions produce value
You think people get meaning and fulfilment from flipping burgers at McDonalds ? Talk about naive. Frankly, it's quite elitist to assume that a majority of people are performing meaningful and fulfilling jobs, a lot of people do jobs they absolutely hate.
> Not working is a sucking void of boredom, nihilism, hedonism, and despair
You're presenting a false dichotomy. I'm not talking about not doing any work, I'm talking about not a having a job. There is a huge difference between doing something because you enjoy it and it gives you meaning, and doing something because you need the money to survive.
Not having a job doesn't mean you have to sit on your ass all day, it means that you get to decide what to do with your time. You can do any number of things that are meaningful to you. It's about having the freedom to decide how you spend your time on this earth. It's quite condescending to assume that people can't find a meaningful and fulfilling way to spend their time if there isn't someone who tells them what to do.
If no people like doing that, than who will do it? Who will do the hard or nasty jobs that nobody likes to do? Where are you going to eat your next McDonald's burger? Cuz all restaurants will be closed cuz nobody really likes doing that full time but it pays the bills.
There are just so many jobs that need to be done and there's nobody that likes them. Who would pick the garbage up? Who would unclog the sewer? Who would drill for petrol or mine for coal? If I got my regular salary without needing to do anything, then I wouldn't go into any of these jobs for sure. Would you?
The words "most" and "many" there are doing some herculean lifting.
Look at the kind of people who do not have to work. Do they still work? No. Some sit on a beach and never lift a finger again, some become creatives and some try to recreate their successes again. None work what would be an engaging and productful job at a take-away joint.
That is in fact not true. Plenty of retirees seek out job-like things. I have a couple of examples.
A small one is my dad. He was a software developer, but thanks to Y2K consulting, he made bank and retired early. After, he spent half the year in Mexico. One of the friends he made there was a teacher. My dad ended up volunteering in the school. He had a part-time-job-like schedule and did teacher's aide things. He loved it.
On a bigger scale: In Michigan there is an arcade chain, Pinball Pete's. It was founded by Tim Arnold in 1976. I grew up there gave them a lot of quarters over years. He sold it in 1990 and retired to Las Vegas, bringing his extensive collection of arcade machines.
For a while he was doing an open house; once a month he'd let people in to play some of his collection. By 2009, he had started the Pinball Hall of Fame, a nonprofit arcade. A couple years back they moved to the Strip and expanded significantly. I was there recently and he spends hours a day there. Opening up. Collecting the quarters. Fixing machines. Telling kids to stop running.
The guy is circa 70 and he can do whatever he wants. What he wants to do is work at an arcade. He'll keep doing it until he dies.
The labor force participation rate among the general population is ~60%. Among those 65-74, it's 25%. And that's not accounting for people who can't retire. It also doesn't account for those who want to work but are unable.
I don't think that's particularly good evidence for that. You're confusing "has a job" with "is working" and you are ignoring the age effects that are the whole reason retirement exists in the first place.
So what you're saying is that when people have more guaranteed income uncoupled from a job they have to do, in this case in the form of a retirement, they can and do choose to do lots of meaningful, enjoyable work? Which I think is the original point in this discussion?
> Look at the kind of people who do not have to work. Do they still work? No.
I'm not sure HN discussions have original points, really. But people do have specific points, and it sounds like you and I both agree that the one I'm replying to is too broad.
Humanity hasn't learned to automate "art". Humanity has learned to automate some aspects of technical aspects of creating images and to imitate some prevailing styles.
I mean, we've done the same with farming. Is it 100% automated? No, not at all, but we've removed something like 99% of the human labor involved that would have occurred around 200 years ago.
Player pianos were invented in 1896, yet we don't consider piano playing to be a dead art. Indeed I don't believe people even pay to see player pianos play, where as they will flock to see even the most mediocre and novice players if they're the right humans.
Art without humanity isn't art. Farming can exist without humanity because we need the output to sustain ourselves. But take the humanity out of art, and no one is interested in it.
The difference is that player pianos can only replay previously existing songs, while Midjourney can create something novel in under a minute. The problem that's being solved is not everyone wants to spend thousands of hours learning how to draw in order to have the (artistically competent) end product in their hands.
Most cases of people paying to see human performers are of performing already-written music though, so I doubt think that's the drawcard.
Actually I don't think anyone truly knows why we obviously gain something from watching live performers that can't be obtained from watching them even on the best quality home entertainment system imaginable (*), but at least part of it is feeling like you're part of the performance, knowing that the performers feed off the reactions of the audience etc.
(*) And why has there never been a market for broadcasting music performances in cinemas?
We pretty much do consider piano playing to be a dead art. You're much more likely to hear recorded music of some sort than a live performance. It's very niche today.
Watching live piano performances has always been niche. The point is that the player piano didn’t replace them, but moreover player piano concerts aren’t even a thing. The human element turns out to be an important factor here.
No it wasn't. Time was almost every British pub had a piano and that's where your musical entertainment came from. All music was live because what other choice was there? The particular form varied by culture of course: mine was more ceilidh oriented.
I dunno, I feel like there's something qualitatively different between pub music used to liven the atmosphere of a venue, where the primary activity is socializing with your friends and consuming alcohol; and art, which is what we're talking about. That is, just because a piano is used to create art, doesn't mean that everything that comes out of a piano is art. I think that applies to Midjourney as well.
But electronic computer music (including pianos) allows us to enjoy many more genres of music nowadays than it was some while ago when only "the elevated" afforded to go to a piano concert.
You're right of course. I should have tapped 'most commercially viable art.'
Graphic designers, corporate advertising, media productions; video game artwork, the artistic channels where many creatives earn a square meal even if it isn't the most human and soulful type of art.
Maybe if you didn't need to work you would have time to fix those problems yourself and get satisfaction out of doing something that directly benefits you.
Ya know, I have helped neighbors with those exact problems. For free. It was nice to be helpful. I would not however do it for fun every day for strangers.
No one is arguing for you to either stop helping your neighbors for free nor to do it every day for strangers, so I really don't see the point in this.
GGGGP: The point of life is not to need jobs in order to survive, the point of life is enjoyment
GGGP: Well, for most people, if they don't have to have a job, their life becomes a sucking void of boredom. These are the only two options
GGP: Nope, plenty of jobs can be a sucking void of boredom for people. It's not like having to clean toilets in order not to starve is incredibly meaningful for the people that have to do it
GP: Well, I like helping neighbors for free sometimes. But I wouldn't want to do it every day for strangers
P (me): I don't see the connection. You literally said you enjoyed doing something for free, so you're not talking about jobs. You could still do it if you didn't need a job to survive, nor would not needing a job to survive force you to do it for fun for strangers.
In any case, it's clear we interpreted the previous messages in a very different manner. In particular, as I've said elsewhere, people seem to be confusing jobs with work. Not needing jobs is not the same as people having to stop working, usually quite the contrary - people would be free to work more on stuff that they enjoy.
People here are extremely privileged and most likely have been for the entirety of their lives, keep this in mind.
Jobs, for the vast majority of people, is just a mean to make ends meet. There's nothing transcendental about it. Just a blunt "gotta pay the bills".
I may make 6 figures now, but I remember life when I didn't know if I was gonna be homeless next month. Perhaps that helped me keep my feet on the ground.
The French have a saying "Life begins after retirement". They find meaning, fulfillment and contentment in, for example, stretching a meal out over 4 hours through conversation.
Whether the French viewpoint or the American viewpoint is healthier can be found in the mortality rates.
> We need something valuable to do and most are incapable of summoning valuable ideas and tasks from the ether.
If quitting a job leaves you with no apparent valuable work to do in your life, that's probably a sign of being only engaged with the world through your job. There are never-ending lists of useful things to for family, for friends, for groups/organizations/churches you're part of, for the neighborhood you live in... and that's before even thinking about personal projects that are useful to yourself.
Sorry, I really bristled at this comment. People who are engaged in the world and have accepted responsibility in areas that aren't solely their job don't have to summon valuable ideas and tasks from the ether. You won't find the bottom of the to-do list. Not bullshitting.
Most people find meaning, fulfillment, even contentment in working, especially when the problems are engaging and the solutions produce value.
You can do that without it being a job. I enjoy making things out of epoxy resin. It's fun, creative, hard work. I'd do it a lot more if we had universal basic income. It's not my job.
I think people are confusing having a job with work. Making things out of epoxy resin takes a lot of work and it's satisfying. If everyone had UBI people would absolutely still work a lot. It's just that they wouldn't have to have a job in order not to become destitute.
Yeah, I am confused by the idea that not being forced to work to stay alive means your can't (or won't, whatever) find anything of worth to do with your life.
Where did that unexamined assumption come from? Do they care about nothing other than standard employment based "work" and so never considered doing something other than staring at a wall when they're not doing it?
Family. Friends. Volunteering. Gardening. Games. Hobbies. Learning to play music, or cook, or who knows... studying biochemistry and doing that because it's rewarding and easier to do in a setting with more people in the same place. Or starting a company if that's your thing, or call it an open-X project and build a community that doesn't require "work" to contribute.
I'm so confused, why on Earth would the agency to choose be bad, it's so patronizing.
There's some serious class bias going on here. There is a certain segment of the population that will find productive work to do that give their life meaning if left to their own devices. There is another segment that absolutely will become blobs or worse (engage in mischief, anti-social behavior, etc). Those who have only ever known folks from the former category see only positives from a future without the necessity of work. Those who know folks from the latter category, well we fear such a future.
Another strange class bias is that those from the (lets call it) "productive" class are absolutely convinced everyone is like them and if only given the opportunity they would be just as productive and fulfilled as they are. Some of us know better.
"Class bias" is a really weird word to use here to talk about that. It's class bias to assume that blue-collar workers aren't intrinsically lazy and that they might find meaningful activities to do if they had the time/energy to do so?
This is the first time I've ever seen "people need work for meaning, and they literally don't have the inclination/drive to find meaning in their lives unless they're forced to work under the threat of losing their livihoods" represented as solidarity with the working class. I don't think most people would consider that perspective to be synonymous with class consciousness.
I think it's more subtle than that - I'd suggest for many of us, regardless of class, the whole reason work gives us meaning is because you know you're providing services that contribute towards society. That knowledge partly comes from seeing that the company you work for (or even run yourself) brings in at least enough revenue to pay its workers' salaries in order for them to enjoy a decent standard living. It's not so hard to believe that a future where there's simply no need for the vast majority of us to work at all will leave many of us feeling like we no longer contribute much towards society, which is likely to be at least somewhat detrimental to our sense of self-worth and purpose etc. But whether that's likely to be a widespread catastrophic issue I don't think anybody really knows. After all, for centuries the undeniable contribution women made towards society was never recognised via a pay cheque.
Yes, this will be a major catastrophe if we don't plan ahead.
I think it's coming one way or another.
For an increasing number of us, the costs of automation will be lower than the cost of living. It will happen quickly. We absolutely need a serious safety net or it will be chaos.
And we need to discover another way to find meaning in what we do, or else it will be a mental health catastrophe.
I have thought on this long and hard and am confident I can find meaning in my life even if a computer can do what I enjoy more productively. It will take getting used to. It won't be comfortable. It is necessary.
It will be very bad if only a tiny fraction of people have financial security.
I use the term class bias mainly because I couldn't find a better term. But it is unique to a particular class to see oneself as the ideal that others are held back from reaching due to environment or circumstance. It's the reason why progressives think conservatives vote against their own interests and would see things the way progressives do if only they were better educated. It's just a fundamental inability to recognize that other people are different and aren't motivated by the same things. What's so insidious about this thinking is that its framed as benevolence. But the mistake is thinking that your way is intrinsically more valuable and so it must be a disparagement to assume that not everyone can reach the intrinsic good that you have reached.
You want to see what people get up to when they have endless free time, just see what idle young men get up to.
Adding on what the sibling comment said, meaning and fulfillment aren't just about the work one does, its about the social role that work facilitates. You may hate your job yet derive meaning from being a provider, from being the man of the family, being a hard worker, and so on. We're already in the process of destroying social connections with ones community and we're seeing a widespread crisis of loneliness as a result. Take away the meaning that work provides (regardless of job) and you basically destroy whats left of meaning in a good portion of people's lives.
> What's so insidious about this thinking is that its framed as benevolence.
Again, I want to remind the context of this: the context is that you're saying we need to force people to work under the threat of losing their livelihood or they can't be fulfilled.
And you're phrasing this as if I'm coming in and colonizing blue-collar workers or pushing my ideals on them. I don't think "benevolence" is the right word to use here, I just don't think there's anything noble about forcing people to work and saying that it's for their own good. It's an interesting turn of phrase to write about this like it's a "culture" when -- again -- the conversation is about whether or not people in blue-collar positions are too lazy and unmotivated to find meaning unless they're forced to work.
I just... it's wild to hear that phrased using the terms you're using. And I wonder if those blue-collar workers would agree that guaranteed income would be "taking away" their purposes, because most of the blue-collar workers I know are much more engaged in social institutions than the white-collar workers around them, and are therefore probably more prepared to find meaning within their communities and families outside of work than the average programmer on HN is.
> You want to see what people get up to when they have endless free time, just see what idle young men get up to.
This is me imposing my culture on other people? Pointing out that you're basically comparing blue-collar workers to lazy youth? Come on.
We derive tremendous value from blue-collar workers that hold up white-collar jobs and allow society to continue to function, even though they're often paid significantly less than us for what is arguably more important work. The least we can do is not pretend that this arrangement is somehow created for their benefit. This has all the energy of the proletariat complaining that the rabble can't take care of themselves and how the actually offensive thing is suggesting that they can.
If only HN could get out of its bubble and empathize more with the average worker, then it would realize that the average worker is lazy and unmotivated and needs to be managed /s
If only gpt4 could tell people what to do in order to find meaning. Surely it understands the human condition at least as well as market forces.
/s
Wait, no actually from what I've seen gpt4 might be more empathetic to the idea that people deserve to find their own meaning in life without their betters giving them a purpose.
"Idle young men", oof. So, so patronizing, like people who think fast food jobs are only for high school kids.
>the context is that you're saying we need to force people to work under the threat of losing their livelihood or they can't be fulfilled.
That's one (bad) way to frame the context of the conversation. The better way is that the need to work is intrinsic to our psyche and core to our self-worth, but the ability to self-actualize is not. The need to constantly work has been a steady feature of our environment ever since we left the trees. Self-actualization, on the other hand, has not historically been a part of this. Meaning in human lives has largely been external, deriving from one's place in the social hierarchy. And work was a key facilitator in securing ones social status.
It should be a given that drastically changing the environment away from the historical baseline will have serious psychological ramifications. The progress of technology has had strong impact, but the social environment overlaid on the technological milieu has largely remained constant. So people got by mostly just fine. The internet has changed this calculus and we've seen widespread psychological damage as a result. AI stands to explosively accelerate this transformation.
What I am asking is whether people as a whole will be better off without necessary work being a driving force in their lives. People like you take it as axiomatic that a post-work society will be better, and offer misplaced moralistic arguments in favor of it. All I am saying is that its absolutely not axiomatic and should be considered directly on its merits and demerits. We've already seen many of the problems I'm talking about materialize.
>And I wonder if those blue-collar workers would agree that guaranteed income would be "taking away" their purposes
For gods sakes, this has nothing to do with the blue collar, white collar division. It's a division between the self-actualizers and non-self-actualizers. I used "class" as a generic grouping term. Although I expect the non-self-actualizers to be overrepresented among blue collar workers. That is, people who don't have the skill or the interest to engage in intellectual pursuits, but just want to make an honest living and take pride in their work.
>The least we can do is not pretend that this arrangement is somehow created for their benefit.
That's obviously not what I'm doing. Spare me these silly moralistic arguments. We need to be willing to discuss this issue as plainly as we can, not be hamstrung by misplaced political correctness.
> That's one (bad) way to frame the context of the conversation.
Is it actually a bad way to frame the context? Are you not saying that people need to be forced to work for their own benefit under the threat of losing their income? What you're saying is:
> What I am asking is whether people as a whole will be better off without necessary work being a driving force in their lives.
So... yeah, you're saying that people will be worse-off without an external force making them work, and it's good for them that they're forced to work. I think my phrasing is entirely accurate here. Losing the income requirement to work is the part you're concerned about, because stuff like UBI only gets rid of the requirement to work for income, it doesn't get rid of any social status that would be associated with work.
You're worried about people not needing to work for their financial security, and you're saying it's bad for them if they don't have a requirement to work for their financial security.
> although I expect the non-self-actualizers to be overrepresented among blue collar workers. That is, people who don't have the skill or the interest to engage in intellectual pursuits, but just want to make an honest living and take pride in their work.
You keep phrasing this like it's a compliment, but being able to make an honest living and being able to take pride in one's work has nothing to do with one's ability to self actualize. I'd push back again on this characterization -- the "non-self-actualizers" I know that make an honest living tend to be very involved in their communities. They go to church, they have social connections, they form meaningful relationships, they marry and have kids. They actually do stuff outside of work.
Self-actualization is not at all the same thing as whether or not you like academic pursuits.
----
I don't know whether or not a post-work society will have its own challenges or if it will be better, and I don't know if it's feasible to build one in the first place. I don't even know that people should be worried about GPT at all, I'm not sure it actually is going to take everyone's jobs. I don't think we're particularly close to a post-work-society, and I think programs like UBI are severely under-studied for the amount of praise they get.
But I do know that we're not doing people a favor by threatening them with financial destitution if they don't work.
And call that moralizing if you want, I'm fine with that. Call it politically correct, call it denying reality, whatever. But don't pretend that it's less empathetic to suggest that someone who doesn't go to college or learn to program isn't going to be intrinsically worse at self-actualization than everyone else. Don't phrase that like it's some kind of solidarity to call people unmotivated.
Yes, people struggle with deriving meaning outside of work, but that does not fit neatly into any singular social category, and it has a lot more to do with one's relationship with one's community and integration into non-work social institutions than it has to do with whether or not someone went to college.
>Are you not saying that people need to be forced to work for their own benefit under the threat of losing their income? What you're saying is:
Presumably you would take an antivaxxer to be dishonest by framing a vaccine mandate as "forcibly injecting me with chemicals against my will". This is no different. Stripping context alters the meaning and is dishonest. Notice how you defend this framing instead of just accepting my original words. It's clearly intended to give your argument some rhetorical benefit without needing to be explicit. This is a dishonest debate tactic.
One important difference is that no one is forcing anyone to work, that is simply the natural state of existence. There is freedom in battling against nature's cruelty. This is not equal to being forced to work at the end of a whip. Your phrasing doesn't distinguish between the two, mine does.
>You're worried about people not needing to work for their financial security, and you're saying it's bad for them if they don't have a requirement to work for their financial security.
I'll accept this phrasing. But notice it is importantly different than "being forced to work".
>You keep phrasing this like it's a compliment
I'm not ascribing any valence in my statements. I am being as neutral and non-judgmental as possible.
> but being able to make an honest living and being able to take pride in one's work has nothing to do with one's ability to self actualize.
Didn't say it did. Self-actualization is the process by which one derives meaning outside of their work/career. The point was that people who "just want to make an honest living" are generally not the self-actualizers.
>the "non-self-actualizers" I know that make an honest living tend to be very involved in their communities.
I agree. But the trends against church-going and community participation are steady. There is every reason to think those connections will eventually be severed for the working class folks as well.
>Self-actualization is not at all the same thing as whether or not you like academic pursuits.
Obviously. But academic pursuits are one avenue for self-actualization that the tech-class points to as ways people will fill the meaning gap in the future. The point is that this avenue is only viable for a relatively small percentage.
>Don't phrase that like it's some kind of solidarity to call people unmotivated.
That's just projection if anything. I'm interested in describing the world as it actually is so we can have an honest discussion about how not to drive society off a cliff. For some reason its damn near impossible to have honest discussions these days.
> Presumably you would take an antivaxxer to be dishonest by framing a vaccine mandate as "forcibly injecting me with chemicals against my will".
A mandated vaccine means that some people are going to get injected with a chemical against their will, yes. We can quibble over the tone, but it is correctly phrased.
> One important difference is that no one is forcing anyone to work, that is simply the natural state of existence.
If you're actively opposed to efforts to change, then that's a very different situation. The context of this conversation is an author saying they wish GPT didn't exist, because they see GPT automating work as a real possibility.
If someone is opposing an attempt to transition to a post-work society, that is not just being in touch with the natural order -- it is an attempt to keep the natural order as it is. So yeah, I would classify that as playing an active role in forcing people to work. Again, I think that's just an accurate description of the position you're espousing; you might not like the tone, but you are encouraging us not to do anything about that natural state.
> The point was that people who "just want to make an honest living" are generally not the self-actualizers.
I disagree with this entirely. Most "down-to-earth" people I know are more engaged in fulfilling activities outside of work than academics are and have stronger connections to their communities in my experience. I don't think there are any stats to back up the idea that working-class/blue-collar workers are less positioned than tech workers to find meaning outside of work.
I don't just think that it's vaguely insulting to characterize blue-collar workers as if they're somehow more prone to being unable to self-actualize, a process that has nothing to do with one's education level -- I think if anything it might be the opposite. Silicon Valley is rife with people talking about how their companies and achievements define them, and is rife with people asking workers to "put in the grind" and "push through" to make something amazing. And I have never heard a blue-collar worker tell me that their identity and value as a person is based on their job as a sanitation worker.
> But the trends against church-going and community participation are steady.
This is particularly weird to hear, because trends against community participation have a great deal to do with the fact that our society increasingly pressures people to replace those institutions with jobs. There is a strong push to have your friends be your work friends, to have your meaning be what you do in your job.
And the increased drive towards validating ones identity through one's job inherently encourages people to disregard other social institutions or non-economic relationships that don't fit into that framework.
----
> For some reason its damn near impossible to have honest discussions these days.
This conversation has moved from:
> those from the (lets call it) "productive" class are absolutely convinced everyone is like them and if only given the opportunity they would be just as productive and fulfilled as they are. Some of us know better.
to
> What's so insidious about this thinking is that its framed as benevolence. But the mistake is thinking that your way is intrinsically more valuable and so it must be a disparagement to assume that not everyone can reach the intrinsic good that you have reached.
to
> You want to see what people get up to when they have endless free time, just see what idle young men get up to.
to finally
> I'm not ascribing any valence in my statements. I am being as neutral and non-judgmental as possible.
>I think that's just an accurate description of the position you're espousing; you might not like the tone, but you are encouraging us not to do anything about that natural state.
We've wasted enough time debating semantics.
>I disagree with this entirely. Most "down-to-earth" people I know are more engaged in fulfilling activities outside of work than academics are and have stronger connections to their communities in my experience.
This may be true; I have no horse in this particular race. The substantive issue isn't which class is more represented among the non-self-actualizers, but what proportion of people fall into this category and what a post-work society looks like for them. I don't know how we ended up spending so much time on the tangential point of who are the non-self-actualizers.
>This is particularly weird to hear, because trends against community participation have a great deal to do with the fact that our society increasingly pressures people to replace those institutions with jobs. There is a strong push to have your friends be your work friends, to have your meaning be what you do in your job.
I'm not sure I understand what this means, but this doesn't sound right. The secularization of society isn't due to work pressure, nor is the disconnection from your local community. The latter is due to the pressures and competition of the modern world, the fact that people move frequently and so do not have "roots" in their local community, multiculturalism that creates barriers between people geographically close people, and so on.
>And the increased drive towards validating ones identity through one's job inherently encourages people to disregard other social institutions or non-economic relationships that don't fit into that framework.
Similarly, I'm not sure this gets the cause and effect correct. We increasingly validate ourselves through our jobs because of the loss of other means of validation.
>This is some revisionism.
Perhaps if you were more interested in understanding my points than finding things to nitpick, you would recognize that my point about being non-judgmental was towards my characterization of the self-actualizers and non-self-actualizers, and how the working class fits in. You gave my claims a moral prognosis, not me. I only defended against unproductive valence claims.
> The secularization of society isn't due to work pressure, nor is the disconnection from your local community. The latter is due to the pressures and competition of the modern world
Where do those competitions and pressures come from? If someone feels a strong pressure to make a career for themselves, to get out of their hometown -- that doesn't read to you as being something that's related to the status we've placed on career and work?
What do the stats say about why people typically move away from their hometown communities? I'm going to guess that job opportunities will be a pretty large proportion of answers in any survey about that.
> multiculturalism that creates barriers between people geographically close people
Hm.
> We increasingly validate ourselves through our jobs because of the loss of other means of validation.
I disagree, but sure. It's hard to clearly establish cause and effect when looking at correlations, and there are multiple ways to read the correlation between a decline in social institutions and an increase in people using work to self-actualize. I'll grant that.
----
> You gave my claims a moral prognosis, not me. I only defended against unproductive valence claims.
You very literally, directly compared people who have trouble finding meaning outside of work to idle children.
> There is a certain segment of the population that will find productive work to do that give their life meaning if left to their own devices. There is another segment that absolutely will become blobs or worse (engage in mischief, anti-social behavior, etc).
Even if that is true, and I very much doubt that it is, a big chunk of the "productive" segment's work will be to help the other segment. People already do that a lot by volunteering. Imagine how much more people could psychologists, social workers, and others help if they don't have to worry about their own livelihoods?
I don't find that plausible. People volunteer to help those who naturally garner sympathy (poor, homeless, invalid, etc). There won't be much sympathy for those that don't have the disposition to self-actualize meaning like the "productive" class. On the other hand, those in the unproductive class won't want this kind of "help" either.
What we need are new institutions to fill the role of providing social connection and meaning. Things that churches and clubs used to provide. But how to revive those things is its own issue.
> Things that churches and clubs used to provide. But how to revive those things is its own issue.
Would reviving communal institutions be a meaningful and useful activity for people to do? Part of the reason why we rely less on community and social institutions is because we are relying on other things (like work) to fulfill that same role. It's not really surprising that people volunteer less at their local church if they're told that their life meaning ought to come from their job.
> People volunteer to help those who naturally garner sympathy (poor, homeless, invalid, etc).
Not really? Plenty of people volunteer to help people in jail, for example.
>On the other hand, those in the unproductive class won't want this kind of "help" either.
People won't want help to find meaning in their lives? I find it hard to believe. Churches and clubs, as you also said, used to (and still do) help provide people with that as well, so I'm not sure you truly believe it either.
>Not really? Plenty of people volunteer to help people in jail, for example.
Of course there are always some number of people that find even unlikely targets sympathetic. But what you're talking about is some kind of widespread movement to help close the meaning gap when something like a third to half of the world is having a crisis of meaning. To have that kind of a movement needs a naturally very sympathetic target, like victims of police brutality. The movement to improve prison conditions is practically non-existent by comparison. I don't find it plausible that the non-self-actualizers will be similarly sympathetic.
>Churches and clubs, as you also said, used to (and still do) help provide people with that as well
I wasn't talking about "help" like how psychologists provide help to their clients. What I mean is an attractive gathering place where people naturally find connection and meaning. People don't want to be "helped", i.e. being made to feel like a charity case, they want to come by meaning and purpose naturally.
Sure some people will be useless. But they are useless now, in the job, producing barely any "value". Might not even be of their own uselessness, there is plenty of useless jobs to go around.
Also, even the "useless" always want more. Even if it is bigger TV and bigger pick-up truck, that would still require work
I agree, for some segment of the population the current definition of "productive" is "meaningful". That's why it will be okay to let people do things they find meaningful.
If Priya had preferred to stay with her family, and there was no financial pressure, the situation would be unambiguously better. Her family may have encouraged her to go to study for family pride -- what if studying and living while studying were free for her and her family had no financial pressure for her to get a job and send money home? I struggle to see who benefits here. Maybe she would have preferred to stay home with her family, maybe she has siblings that she will miss, why would it be up to me at all? I don't get to define productive.
UBI (or whatever mechanism for providing basic needs) also doesn't mean there is no financial reward for employment. She could still go and study and earn money and send it home to a family that doesn't need it badly except now if the job is automated by GPT4 somehow no one suffers. No harm is done other than that she wasted her time studying this thing, but no one is going to suffer because of bad luck beyond wasted time.
There are a number of things that I do think people don't find meaning in doing. Many of these things can be increasingly automated like being a teller or working in a call center, but not all of which can be (for now), like repairing sidewalks. These are a set of things that aren't very fun to do which still need to be done, sure. Oddly the ones I can list off my fingers are not the ones that pay well, so something is certainly not working right on the incentives, sure. I agree that society should reward jobs less if they are meaningful and enjoyable than jobs that no one wants to do, but that's not really how capitalism works.
Plenty of people don't tend to do things even they would consider "productive" in their spare time, but how much of that is because they are under constant financial stress and have so little free time? I believe that if basic needs are met people will generally find more genuine sources of meaning, for them, whether or not I consider those things productive.
But my opinion isn't important here, that's the patronizing part.
I simply do not believe people will sit around and watch TV all day if they are in good health and aren't required to work all the time for security. Or if they do then that's their business, I'd rather try to inspire them to do other things than force them to by withholding food and shelter.
Let people be people and learn what makes their human life meaningful to them rather than trying to starve them into action that you consider productive.
> These are a set of things that aren't very fun to do which still need to be done...[they] are not the ones that pay well
Because they're generally things that don't require extensive training/exceptional skills/abilities to do, hence there lots of possible candidates to take on such jobs.
I wonder what a world where there's billions of us with no job options other than the few remaining disgusting/dangerous jobs that automation can't yet handle will look like...
Here's how I do that thought experiment. Maybe your answer is different.
It will depend on who owns the machines that do the work.
It's not comfortable to think about, but I think it's silly to ignore completely. I've worried about it a lot and am at peace with it, for what it is worth.
If there's a strong safety net and regulations on corporations
No matter who owns the machines that produce things people need, people are able to live comfortably. In that scenario, the world looks like one where those undesirable jobs pay exceptionally well, gain increased respect, and improved working conditions until they're desirable -- because starvation and housing is no longer under immediate threat of being withheld. I don't hate that world, it seems frankly more fair. I think we can agree that more rational decisions are likely to be better, and that forcing people to make decisions that are only rational to them under threat of food and shelter is bad.
It's not like my friends and I in middle school loved doing engineering because we saw dollar signs. We did it because we had a knack for it and liked doing it with no ulterior motive. Forcing people who weren't interested in engineering to be engineers has honestly just never seemed like it worked that great. Give kids opportunities to discover that they find engineering fun instead... there are other means to get to a good place without the threat of food, health, and housing. Much of it education.
But maybe for me, meaningful means going and helping with my friends projects until I'm inspired to make some kind of art or work on a project to make a new idea. Who knows, being productive financially is just not necessarily always what will give me a meaningful life, and we only get one. Lots of things that are meaningful to me aren't productive financially.
If there's not a strong safety net
God help us all. If you don't own the increasingly small number of things that do an increasingly large fraction of all production you are way, way, way more screwed.
If everyone gets free money the optimal move as an individual is to speculate on assets because everyone else will be. The financial rewards from gambling will be higher than working with much, much less effort.
I don’t think many people will find meaning in that world.
The financial reward of "gambling on assets" is already far higher than working with much, much less effort. Except that now only rich people get to do it safely.
Housing is an asset that must be "gambled" in order to live securely and control your residence. I agree that is horribly broken, but everyone deserves a chance to buy assets without my permission.
I also argue that currently poor people under less financial stress will be more able to avoid getting fleeced, and that arguably many are already better at it than plenty of people with inherited wealth.
As a concrete example, mortgage rates being higher for poor people than rich people is already abusive.
If people followed the "optimal move" all the time, assuming you mean it in a financial sense, there wouldn't be any teachers or social workers or librarians.
If everyone gets the relief of knowing they are free to pursue what they like without risk of starving, I imagine it'd be way easier to find meaning in the world than it is now.
What if the reason is that when they come back from 8h job that also took 2h to even get there (coz they are not rich so they live far from it) they just don't have energy to ?
I swear, it's like nobody here actually worked hard for any extended period in their life..
> most are incapable of summoning valuable ideas and tasks from the ether.
Is this really true? It's absolutely not a personal problem for me. I haven't worried about boredom or lack of purpose in decades. My worry is that I'd need a hundred lifetimes to give proper attention to everything I find interesting or meaningful, and the problem gets worse the older I get, the more I learn, the more I find interesting.
What a profoundly naive opinion. The overwhelming majority of paid work available is not fulfilling to anyone, and the overwhelming majority of people who are wealthy enough to not need to work to subsist can find things to do with their time, and for the most part seem to find more fulfilling things to do than people stuck in the labor market
> Most people find meaning, fulfillment, even contentment in working
Only because it’s the only thing they know. If “work” wasn’t a constant in human life you’d see people adapt to finding meaning and fulfillment in something else.
> Many people claim their lives would be better if they never had to work, but they are bullshitting themselves with childhood naivete. Not working is a sucking void of boredom, nihilism, hedonism, and despair
I’ve taken multiple year hiatuses from work (living very cheaply) and they are the best years of my life. Wake up, go for a run/walk, go to the gym, read a book, go to the coffeeshop, make lunch, go to the movies, go on dates, use the internet. Absolutely incredible.
You can be working without it being your only source of income. If everybody was given let’s say ten million dollars in capital (and endless social security), those who wanted could work. The rest of us wouldn’t mind letting the machines do the work.
As any student who takes Econ 101, or reads history, (or has heard of a country called Argentina? or has opened a newspaper during the past year of post-Covid inflation?) will learn, this assumption is factually incorrect. If you give everyone ten million dollars, there will be a phenomenal and rapid increase in the price of goods, especially consumer staples (since everyone got that money, and everyone buys staples).
You can't really just throw money at the demand side of the equation and expect everything else to stay the same. Supply side will raise their prices because they can (when everyone's got $10M in the bank, why not charge $50, $500 or even $5,000 for a loaf of artisan bread? And eventually other producers of bread follow suit because the consumer has become less price sensitive).
If you want to improve everyone's standard of living, what has repeatedly worked throughout history is to lower the cost of production through technology, and ensure there's lots of competition on the supply side. With enough competition, producers are unable to behave like a cartel. Eventually someone cracks and sacrifices part of their margin to attract more customers, and then a price war ensues. A textbook example is salt, which for most of human history was quite expensive, but after mechanized mining techniques were developed it became so cheap that for the average household it's practically free.
Technology + competition. At this moment in history we're quite good at the technology part of the equation but we have allowed many monopolies and oligopolies to form, so we're struggling at the competition part.
Sure if you give everybody 10 million dollars in pieces of paper, what you described happening will happen.
Money is the measure of the productive capacity of an economy. If you increase the money without increasing the capacity then you get inflation. But let's be charitable and assume that "Gud" was talking about increasing the capacity commensurately. Because that's what's happening. AI, robots and almost zero marginal cost green energy are going to increase the productive capacity of economies dramatically over the next decade or two.
> AI, robots and almost zero marginal cost green energy are going to increase the productive capacity of economies dramatically over the next decade or two.
Execting green energy to produce zero marginal cost is probably a bit too optimistic at this point. We have been adding green energy for at least 20 years now and energy keeps getting more expensive. Not even addressing whether its sustainable, but expecting a point at which additional solar panels or wind installations are going are going to produce extra energy at close to zero cost is expecting too much.
You might have that argument with nuclear energy, because most of the cost is upfront. But approval process for that will have to be expedited by congress.
Price is set at the margin. Right now the marginal energy is fossil fuel powered and the quickly increasing share of low cost renewable energy doesn't impact price.
The problem is often technology becomes a barrier to entry especially when it requires scale to operate. AI is the extreme example of this kind of technology - needs large compute, and large amounts of data, and requires a actor with enough capital to create it. In effect a lot of modern technology has helped create monopolies.
The barriers to entry definitely exist, but is it the technology itself that creates them, or is it the intellectual property laws we've adopted? Capital is a barrier but it's far from an insurmountable one -- there's plenty of capital floating around in the world. As a thought experiment imagine what the tech industry might look like if the US introduced some form of compulsory licensing for software (for patents? for copyrighted source code?) like what exists for music.
Natural monopolies certainly exist in sectors of the economy like public utilities, but I don't think they are so strong in tech.
For me monopolies, even natural ones, are maintained due to power structures in society. If you see most natural monopolies that are privately owned there's usually a political system that allows that to occur and a well connected powerful actor. AI has the ability to break the one power structure keeping the middle class intact - that being they still technically need people to "think on the ground" to provide the things they want. i.e. output is still a function of labor. AI breaks the need for "labor" to be a required input into the production line long term - i.e. it will no longer be a large economic factor of production.
My personal view: AI makes most of the world's population in the long run surplus to requirements for people who own capital, societal power and the planet's scarce resources. That's a form of monopoly.
...and what will happen when every single person goes and tries to buy a 50" TV? Hm? Did we suddenly invent a magical TV making machine?
Come on... this is Real Life, not Magical Fairy Land.
We're not talking about a magical cornucopia that generates an endless amount of physical goods that can be used to accommodate the needs of every person.
We're very specifically talking here about technological shift that will eliminate a large pool of skilled jobs.
People will still need jobs, or they will become homeless / starve / have to leave the country.
Why do we need jobs? I’m genuinely curious.
If the machines can produce the food, goods and luxury items traditionally made by mankind and their domesticated animals, I genuinely don’t see the problem.
Naturally this is purely hypothetical, parent argued that work gives meaning to life(which I generally agree with). I argued you can still be working, even if less efficiently than the machines.
Maybe it will be a gradual change. Agriculture and manufacturing is already highly automated, for better or worse.
> Why do we need jobs? I’m genuinely curious. If the machines can produce the food, goods and luxury items traditionally made by mankind and their domesticated animals, I genuinely don’t see the problem.
In principal you're right, we can in theory live like you suggest and expand on leisure culture / volunteering / 'made up' jobs by the government.
In practice, we're super far from the utopia. Energy is expensive, food is expensive, housing is expensive in ChatGPT can't do squat about it. What it CAN do is possibly replace me as a worker.
So that's the conundrum.
> Did we suddenly invent a magical TV making machine?
I mean ... we already have 3D printing, and car making robots, and electronics making robots. Most of the TV is robots.
All that's needed is the equivalent of 3D printing that adds an extra step of "TV-making-robot"-making robots. One reason we don't have that is that it turns out the robot making robot costs more than certain as-yet non-globalized labor markets.
This entire thread is in the context of “gpt is going to destroy jobs”; the arbitrary “we need to disassociate working and basic necessities” isn’t an isolated socialist discourse.
You can wax philosophical all you like, but you’re failing to address the fundamental reality.
There is a physical limit of good and services available right now and no amount of magical posturing will make that untrue.
Anything is possible in the future given unlimited time and resources, but this thread is not about that.
It is about right now, people losing their jobs.
What is being proposed here is not a solution to that problem. The ability for people to build things doesn’t mean they will. It’s pure speculation about what might possibly happen in the future.
> Then we agree on that.
I do not agree with you. You’re just making arbitrary speculative statements.
Sadly, one of the lessons of Covid Era I think is I think like this kind of windfall would just destroy everyone spending discipline, and then prices would just inflate correspondingly.
You can be meaningful and work very hard for other humans and be very valuable without any economic activity.
That’s the point. Working for money is only tangentially related to purpose insofar as your job matches your particular style of “purpose”. If you are free, truly free, would you work in some soulless corporate?
> Most people find meaning, fulfillment, even contentment in working, especially when the problems are engaging and the solutions produce value.
Sure they do. But "value" is not simple one dimensional "I get money for food and rent".
If value of your work is just money, you have to mostly do the things that work toward money
Not making other people's life better or more interesting. Not something that you find fulfilling. But things that make money first, are any of the above second.
Having the basics (let's say "food, money, internet + some spare change to get what you need want") allows individual to pursue things that are risky and might not be profitable in the end without stress of not being able to pay rent next month. You can be a musician that "only" have 10k listeners. You can make niche little gadget that earns maybe $500 a month in sales but enriches other people's lives.
And now corporations would have to offer something substantial (whether in term of being interesting, or profitable enough) to find someone to hire. Less "bullshit jobs", or soul-crushing work that barely affords you a living just because your skills don't align with what is profitable.
> Many people claim their lives would be better if they never had to work, but they are bullshitting themselves with childhood naivete.
Did you never had an interesting hobby in your life ? I have enough that if money was not an issue I'd keep my brain and body involved for years to come.
Additionally, people who hold this belief fail to realize that “I don’t want to work.” ACTUALLY means “I want others to work so I don’t have to.”
For example, how are you going to eat? You are either going to grow, cultivate, and harvest your own food (i.e. work) or you’re expecting others to do that work for you.
Oh, you say it can be “automated”? Well, who’s going to design, build, and maintain the automating machine? That’s all work too!
Given that the article we're discussing is about robots replacing workers, the answer is "AI & robots" for all of your questions.
2 years ago we would both have agreed that that would be impossible. My belief is that most likely AI will hit another roadblock soon, following a "punctuated equilibrium" model so there will still be a large number of non-automatable jobs. But if I'm wrong and the pace of change of the last 2 years continues for another 10...
> the answer is "AI & robots" for all of your questions.
Then who designs, builds, and maintains THOSE AI & robots? It can’t be “AI & robots” all the way down.
>My belief is that most likely AI will hit another roadblock soon, following a "punctuated equilibrium" model so there will still be a large number of non-automatable jobs.
I agree (although it may or may not be “soon”). As history has shown us, technology advancements just cause us to reimagine possibilities and start solving problems that were previously impossible.
For example, as computers have gone from a few bytes of RAM to billions of bytes of memory, humans didn’t say, “ok, we’re all set now.” — we invented whole new classes of software that do all kinds of things unimaginable to the early computer scientists.
> people who hold this belief fail to realize that “I don’t want to work.” ACTUALLY means “I want others to work so I don’t have to.”
No, it means "I am working to generate more wealth which flows predominantly to the owners of capital, who often do no work and sometimes have never done any work at all - can't we do something fairer than this?"
> No, it means "I am working to generate more wealth which flows predominantly to the owners of capital, who often do no work and sometimes have never done any work at all - can't we do something fairer than this?"
It always starts with this, then the next step is "ohh we can't really tax rich people and corporations ('owners of capital' that you speak of) since they have a lot of ways to move their capital out of our reach so let's just fleece the middle class instead!".
Over a hundred countries agreed to a 15% global minimum corporate tax rate starting this year. It's not nearly enough, but it's a start, and it shows we can tax rich people and corporations.
The work that I find meaning and fulfillment in pays about 1/20th of what I get paid at my job, if it pays at all. I do my job because it allows me to allocate the most possible time to fulfilling work (through early retirement), when I can spend all of my time doing nourishing things like cooking for my family and raising children.
What about all the work that's a sucking void of boredom, nihilism, anhedonism, and despair? You're naive and privileged if you think that there's not plenty of that.
And, as others have mentioned, not working for living at a subsistence level does not mean not doing rewarding and value-producing things. Quite the contrary.
Spoken like someone with the privilege of choice and completely blind to it.
How many in this world simply have not had the chance to educate them selves, been lucky with timing or knowing the right people to get the nice jobs where they are listened to and even looked up to?
Where they not only get a salary where they can survive off it without working a second or third job, but are also able to save up some buffer.
That they might actually afford to get out from under landloards that continuously increase their rents, and buy a property of their own.
And so on and so forth.
Your comment drips ignorance on the daily hardships huge swaths of the human population on this planet (including a large group in the rich western world as well) have to go through every day, and the propable relative luxury of your situation compared to theirs.
I don’t know, I think maybe the midwit meme applies here.
(Early) retirement is an adjustment. It takes time to find them, but there are alternative ways of finding fulfillment and I’m happy to have them. N=1 but my revealed preference seems to be that yes, being financially secure is good, it reduces working, and it’s possible to find better alternatives.
There is a difference between "work" and "job" that you ignore here.
Yes, most people find meaning in some kind of work. That doesn't imply that having a boss and worrying about paying your bills is more meaningful than working without a boss and without worries.
> . Most people find meaning, fulfillment, even contentment in working, especially when the problems are engaging and the solutions produce value. Many people claim their lives would be better if they never had to work, but they are bullshitting themselves with childhood naivete.
You're straight up projecting your own personal experiences as a generalized truth. Seriously, grow up and learn that there are a lot of differences in people. You might need this, that doesn't make it into an universal truth that everyone needs it or gets it by having a dayjob.
The only thing that you can say, generally is this: humans can gain happiness by getting acceptance from other people when they care about the people that accept them.
I agree with the other sibling comment about a “job” not being the only way to have that fulfillment.
Also apart from the “real” disabled, a lot of people are just disabled enough mentally or physically to be deemed fit for Jobs with a capital j but are miserable.
> Most people find meaning, fulfillment, even contentment in working, especially when the problems are engaging and the solutions produce value.
The opposite, actually. Most people, for whom a reasonable fulfilling job exists, do not have the opportunity to work such a job. AI does not promise to increase the availability of fulfilling and contentful jobs, meanwhile the cost of living will continue to rise with no end in site while wage stagnation continues another decade.
A comment calling someone "naive" for thinking that work-for-income is the only possible way to find happiness.
Good god, corporate America has utterly brainwashed multiple generations. You lost your creativity, your imaginations and your aspirations. Even your entrepreneurial spirit.
"Here's a machine which can automate the intellectual labor of multiple professions, enabling it to simply execute on ideas you come up with." and the only thing any of you can think of is "but would I do with all this free time if I wasn't desperately struggling for food and shelter?"
This is a nice thought that isn't going to happen. AI will eliminate jobs and rich people will get richer while also widening the moat so you can't use that same tech to compete.
Its really a function of who is paying for the tech, who owns it and what do they want to do with it.
The only reason the middle class was born was because trained workers could pull their labor and affect upper class wealth. They had power. AI takes that power away.
That would be great. It’s also not going to happen without a massive uprising. The people profiting off automation have zero intent of sharing the wealth and every intent of hoarding it.
To over-simplify, revolutions happen when young men get bored, gather into mobs to entertain themselves, and then somebody with a cause directs that mob into action.
The standard way to prevent revolutions is to channel the energy of young men into a productive job and a family.
But today, bored young men entertain themselves with video games etc rather than gathering in mobs to entertain themselves. We don't have large gatherings of aimless young men anymore.
We were all fine with having a bunch of pretty poor people around us (let alone other countries where people live horrible lives).
Why should anyone care white collar people are going to get hurt? Who said we have enough power/motivation to meaningfully revolt?
Why haven't the poor revolted already?
I hope you're right but I don't think its a given this will happen.
When has an uprising (or revolution) been anything other than a disordered mob? I wouldn't expect any such transition to be orderly and well-planned. It will be reactionary in order to quell the chaos.
Yep. That's why there WILL be an uprising. When? I don't know. When the pressure becomes too high to bear, and risking your life seems like a good option compared to just hanging in there. But maybe by that time most humans have been genetically engineered to be happy to be serfs, and oligarchy is a genetic condition now.
I expect we'll adjust the status quo for decades yet. The internet projects a lot of negative sentiment, but I suspect most people are happy scraping by so long as they have a roof and some entertainment.
Even proactive people are made to believe they are just one more "rise and grind" away from being a millionaire, they want to be succesful in this society, so they have no desire to tear it down.
What could bring the stack of cards coming down I think, is a housing affordability crisis. For anyone who has ended up without a home or even just the threat of losing a place to live, you wake up to that reality real quick. If there is suddenly a majority without work and without a home, that's a bunch of people who just found out the system is broken and will want answers.
Still a potential possibility - sadly IMO more so than the utopia vision of AI; thanks for reminding me of this. We simply become fodder for the things AI can't reasonably do in the "real world" until it can with the owners of the systems living it up. At that point the rich/political class have no need for the "rest of us", live the high life and the rest of the population is a "problem" that has to be managed by the state creating mass inequality.
Jobs often make people feel useful. While many can be the happy unemployed person playing Counterstrike 24/7, many others need some sort of occupation for self-realization. This is actually a common problem, which can even became a major psychological issue, with people entering retirement.
Maybe one day we can live in a world where machines are doing all the work and there are fulfilling hobbies for everybody, but I fear this will require more changes, on a much longer time horizon, than the short-term issues just around the corner due to the recent AI advances.
The people at the top of society never had any problem enjoying life while everyone else worked for them. We're just need machines at the bottom of society so that all humans are in the owning class and can enjoy not working.
Bertrand Russell's In Praise of Idleness, 1932 seems increasingly true to me. The richest has kept a monopoly on idleness while tricking everyone else to see work as their purpose in life (to work to make it possible for the rich, idle, people to have nice lives without having to work).
"Modern methods of production have given us the possibility of ease and security for all; we have chosen instead to have overwork for some and starvation for others. Hitherto we have continued to be as energetic as we were before there were machines. In this we have been foolish, but there is no reason to go on being foolish for ever."
Discrimination against poor people, more specifically. No one cares how unemployed you are if you're rich. Or at least well off enough to be reclassified as "eccentric" and thus okay.
Yes, exactly! Imagine as a thought experiment that we can produce everything we do today, but with zero labor due to automation. This would be a miracle for humanity!
For one thing, we could use all our free time however we want, including working to produce still more stuff, or just go hiking.
The real problem is how to distribute the goods and services produced - and there a UBI is probably the right answer.
Machines do all the (necessary) work, UBI ensures that everybody benefits, and humans are left to do as we please.
You’re glossing over a lot of specifics. Who owns the machines? Who dictates how much food you get? Medical care? Who says who can have children? And how many?
Or will this result in infinite food, water, and shelter?
As soon as you rely on UBI to live you’ve lost all control of your own life. Your a child with an allowance. The state has absolute authority over you.
The government is already controlled and influenced primarily by nefarious interests. I can’t even begin to imagine how nasty it gets when the entire population relies on them for mere sustenance.
It doesn't have to be that way. For one thing, you don't need to means test it. Just give the same amount of money to everyone. Then if you work you still end up ahead. So no dis-incentive to work. For another, if implemented properly the amount would go down if production declined, or up if production increases. This way it's self-correcting in the aggregate. As people leave the workforce, the UBI goes down, nudging some people at the margin to go back to work.
But this still leaves people free to choose for themselves, without interference from the government.
Yes. That’s why UBI is a neat idea as a replacement or enhancement for welfare, and other social services. That’s not the context in which we’re discussing it though. We’re discussing it as an alternative to work in a world where almost all human jobs have been automated. In that context it’s not a good solution, and in fact it’s dangerous because it leaves everyone reliant (and obedient) to the government, and a select few mega corps.
If everybody makes the same amount then all you’ve done is inflate the currency. Money is used to control access to finite resources, with the goal to get more tokens than the other person. If you give everybody X tokens per month, then in aggregate things will cost X tokens more.
No inflation required. People buy things from whoever owns the production, and the producers pay high taxes to fund the UBI. No net money creation required.
Then you've created a net deficit. You can't ignore algebra and pay more than it costs to make something and put it on the shelves. Without those paying people to put it on the shelves making more than it costs to pay those people there's no incentive. This is a pipe dream without causing inflation and doing nothing in aggregate.
Good luck trying to tax AGI companies 95% of profits. Perhaps you could strike but you'll be unemployed.
I guess we'll just have to cross our fingers that Sam Altman and friends will pity us enough to give us some pocket money to survive. That's assuming the AGI created is aligned with our values.
I mean, we can keep hoping that AGI will be a good thing with zero evidence or we can take action to slow progress now so we can proceed with caution.
In the history of political movements,
have there been any that have been successful with slowing progress? The Luddites failed to. stop the industrial revolution, despite all the looms they broke. The cat's been released from BagGPT, and even if all the world's countries ban AGI research (somehow), that's just going to drive the work underground, and the first ones to get usefully further along the curve will be able to outcompete any who haven't.
It's a real life prisoners dilemma, with 8 billion prisoners, and the first one to defect get to decide what the fate of the rest of humanity looks like.
Yeah, that's kinda the problem, same with tax evasion; at worst the company would make a subsidiary in country and only make it cost center on balance sheet with all profits going to the tax-haven company
> In the history of political movements, have there been any that have been successful with slowing progress?
Not an argument, unless you believe "we failed in the past so why bother trying now" is sound reasoning.
> The cat's been released from BagGPT
Do you say the same thing about nuclear weapons? I mean, given that the nuclear weapon cat is now out of the bag we might as well see just how big a bang we can make, right? Anyone who wants to stop progress of nuclear weapon development is obviously a Luddite.
And while we're at it, is the fossil fuel cat out of the bag too? Is any effort to try to limit the release of CO2 as a global community pointless?
--------
Please keep an open mind and let me reason with you.
I assume you believe AGI poses some level of risk to humanity. The exact nature of that risk isn't too important – it could be economic risk, political risk, existential risk or all three. Basically I am assuming you believe there are enough things which could go wrong in creating superhuman AGI that a sane species would seek to limit the progress of capability research until we can proceed safely. If we disagree on this please explain why you do not believe AGI poses any risk to humanity. Note, hopeium that things will be okay is not an argument.
Okay, so since we agree that a sane species like us humans would limit AI capability research and proceed cautiously we now need to solve the prisoner dilemma which you correctly identified.
My solution to this would be as follows:
First we need to take this seriously. We need to be frank about the risks we face from AGI and try to educate the public about what may be coming. Currently the general public is so clueless about AI they're either not aware of recent advances, or they believe silly things like it being possible to unplug an AGI, or program it to be good.
Secondly, we need to establish an independent international organisation to oversee state-of-the-art AI research. Any country which does not agree to this will be sanctioned and as a global community we must agree do everything we can to pressure those countries to cooperate. In my opinion this includes war, but that's only because I believe AI is a significantly large existential risk to humanity that this is necessary. Appropriate actions in practise would obviously need to be debated and agreed upon as a global community.
Thirdly, we need a way to increase global trust and transparency of AI research. To do this I would propose the creation of a global AI whistle blowing fund. All countries which are part of the international agreement to oversee state-of-the-art AI research would be required to contribute to this fund annually. This fund would allow citizens from any country in the world to come forward with evidence against corporations, governments or individuals in violation of the agreement. These citizens would then receive a reward for their information and protection from any country (of their choosing) which signed on to the agreement. By incentivising whistle blowing it would be hard (although admittedly not impossible) for any large research project to take place.
Fourthly, fund and research ways to identify and limit unauthorised AI projects via technology and audits of things like GPUs orders. Simply limiting the distribution and capabilities of GPUs at a global level would be one of the easiest ways to ensure AI capability research can't advance too quickly. Of course we would need countries like China to play ball, but so long as we can do this in a transparent way and they understand the risks to humanity should they not corporate they would have no reason not to. This isn't too different from limiting the development of nuclear weapons as a global community which we have been quite successful at doing.
Finally, all AI research projects which are approved should be done at an international level for the benefit of all of humanity and research teams must detail how they are approaching safety and publish all safety research. Additionally, there should be government grants into things like alignment research to better prepare us for superhuman AGI.
What I'm proposing obviously isn't perfect. In the same way we can't guarantee nuclear weapons won't be created in the future, we also can't limit the risk of AGI entirely. Instead a more reasonable goal of slowing capability research while increasing safety research as much as possible should be pursued. There is a possible future where AGI will be great for humanity and our goal should be to maximise the chance of that outcome. The goal is not to "limit progress". Even if we disagree about exact actions to take there is no alternative world in which it is reasonable to allow a handful of billionaires to continue AI capability research unregulated while crossing our fingers that the AIs they create will be aligned with our values and that they pity us enough to give us food and shelter once we are all unemployed and fully dependent on their creations.
> I guess we'll just have to cross our fingers that Sam Altman and friends will pity us enough to give us some pocket money to survive. That's assuming the AGI created is aligned with our values.
My guess is that Altman and co. already have some kind of exit strategy (like fleeing to New Zealand after they've captured a huge chunk of the developed world's wealth).
The big issue is the transition. What happens when we still need around 30% employment to keep things going. Neither enough automation for everyone to take permanent holiday nor enough labour to go around for everyone to make the current way sustainable. I have no good answer for how to address this middle point.
I think you start with a kind of non-profit member-owned "general automation corp." that supplies a level of basic QoL: clean water, food, shelter, clothing, energy, internet, medical, etc. per-member, at a set rate, say US$300 per month. That is, you pay in $300/mo. and that covers your rent, food, utilities, health insurance, etc. Over time the rate you pay falls to zero and remains there for the rest of your life.
The task of the corporation is to supply the above goods and services efficiently, in environmentally regenerative ways, while meeting or exceeding minimum quality standards.
- - - -
It's kind of like a new economic regime developing within the old one, the way a crystal precipitates out of a saturated solution, eh? A sort of phase change?
No, of course not. I don't understand what you are imagining.
I'm talking about forming a non-profit mutual-benefit corporation and offering memberships which include services. Not forcing anyone to do or adopt anything.
> You don’t see a problem with forcing people to do something they don’t want?
I do see a problem with that. It's called "coercion" and I am against it in almost all of its forms. (I do recognize a pragmatic need for e.g. laws and police and the legal system, but by and large I'm in favor of freedom and self-determination for everyone.)
> This is scary, some people seem to be so gleeful at the idea of AI taking over everything they’re willing to resort to force to make it happen.
Again, I don't understand what you are imagining. I'm not sure how you got "forced adoption" from what I said, but I appreciate any feedback to improve my communications. Cheers!
Bring this back to the real world then, how can this happen? If it's possible then someone who doesn't care about profit would create this already. Therefore not possible without forced adoption.
> Bring this back to the real world then, how can this happen? If it's possible then someone who doesn't care about profit would create this already.
I'm doing it. I'm that "someone who doesn't care about profit". I literally went to start a normal corporation, saw this "non-profit mutual-benefit" corporate form, and realized that it aligned better with what I wanted to build, so I incorporated as that.
The idea is to acquire some land, lay in a kind of ecologically harmonious high-tech neighborhood combined with a 3D printing shop and other facilities (electric, ISP, food forest, etc.) and rent-to-own or something to members. It's a kind of economic time travel to a Star Trek-style techno-utopia (to the extent that such a thing is even possible, given human nature, eh? But that's not my problem. I'm just trying to keep from messing up the environment and/or becoming a peasant, you know?)
Check out https://www.riverbed-ranch.com/ for something like what I'm talking about (this is not my thing, but it's got some similarities.) These folks are basically treating Utah like a fresh alien planet and building a nice modern eco-friendly town out there.
I agree! The problem is not with the fact that AI will make a lot of people unemployed, the problem is how we treat people who are unemployed.
I love what I do, but I love the fact even more that I don't have to do it to live a good life (or worse: survive). I do it out of pure curiosity or maybe altruism. Maybe even social status, but not for the money.
Sure, that would be great but history has shown this is a beautiful but naive pipe dream. It doesn't take into account the ambition and greed of humans and their capacity to exploit others.
Which means they could also push us over the edge. If the weak-minded are currently influenced by today's bots, it's a matter of time until some are testing humans by "pushing limits" if you will
> Which means they could also push us over the edge.
Sure, but that's a separate problem, eh?
We split the atom and built both bombs and power plants, it's a choice we have to make: which to deploy?
We have (or are about to have) the technology to cure psychological and emotional issues at scale. (A good therapist today runs about (I don't know?) $150/hour? Way out of reach for most of us without insurance or subsidy or something, eh? What if that was e.g. $0.0000015/hour?)
>> The point of life is not working, the point of life is to enjoy it. We should strive to eliminate as many jobs as we possibly can, the less we have to work the better it is.
As humans we have not found a way to allow people not to work. Anyone not working is either living off money from their own prior work or benefitting from the work of someone else. Let's see and validate such a system before we run off eliminating jobs.
There’s always the joke about the “Communist Utopia,” but that’s what it was marketed as. The marketing was also so strong people killed their own by the millions to make it happen. It never happened and we remember those eras for atrocities, not Utopian equality.
While true, it seems less likely that we'll somehow solve the myriad political challenges to enable universal income than the possibility that AI tools will cause a further concentration of wealth in a small number of hands.
while there's a case for idealism, without some degree of pragmatism we'll be lost on policy or regulation proposals.
Yes, policy needs to be pragmatic in how it ensures that trends toward greater inequality are reversed. In particular, anti-trust regulation, non-means-tested social safety nets (IE government services that allow humans to survive), and meaningful investment in real public infrastructure (Not public-private partnerships, as currently run the internet and the electric grid of most of the United States, for example) seem like good places to start. There is only so much concentration of power that can occur before bloodshed becomes inevitable, and proposals of this kind are attempts to solve problems for people on the ground without anyone needing to overthrow the extant society or perish. Attempts to frame such common-sense measures as attempts to overthrow society themselves are done out of profoundly myopic short-termism
During lockdowns the rate of depression and all sorts of mental and physical issues went up. Becoming unemployed may not be the exact same thing as a lockdown but less incentive to get up at a reasonable time or to leave the house would still lead to more overweight, lazy and depressed people.
> less incentive to get up at a reasonable time or to leave the house
People have plenty of natural incentives to leave the house ("reasonable time" is a sign of your own biases, but no doubt leaving the house is healthy regardless). The reason people don't do so is because there are strong economic disincentives to do so. This is not just obvious conscious disincentives like "I don't have time because I need to earn money online" & "I will have to pay for X, Y, Z in the city if I go out" but also much deeper more complex systematic disincentives like "I am chronically ill due to years of economically-linked stress and burnout" & "I feel depressed due to economically-linked lifelong trauma"
Healthy people don't need employers to incentivise them to leave the house. And unhealthy people don't need work, they need support.
Becoming unemployed may not be the exact same thing as a lockdown during a pandemic? Don't you think people dying in the hundreds of thousands due to disease has more to do with rise in depression than anything else?
Countless people die every day to all kinds of horrible diseases and most people were not even affected. Guess what there is even a war going on, tuberculosis, cancer and still covid.
I'm not sure there is objectively a point of life, but what people need is a sense of purpose -- just enjoying life doesn't work. For many, their job is a large source of purpose.
According to whom is the point of life is to enjoy it? There are different cultures and societies in the world. According to my faith and traditions, the point of life is to worship God. Of course we still strive to avoid suffering and to make things nice and appealing and safe and and, but we know that at the end of the day, we are all being tested and it can all be taken away from us at any moment, no matter how much we achieve.
> To make this possible we need to find a way to a new system that doesn't directly link labour with income.
As others have pointed out, this is an incredibly naive opinion. Labor is tied to income precisely because it happened organically, not because a group of self-appointed individuals decided to develop a "system". Most attempts to develop alternative (read: non-organic or top-down) systems for organizing human societies have either failed entirely or have been short-lived.
I see this sentiment expressed in almost every venue of discussion, but I never see a concrete plan, or even steps we could take right now to progress towards that future. That's why I'll always remain skeptical about technological utopianism. It simply doesn't work that way in reality.
> The point of life is not working, the point of life is to enjoy it. We should strive to eliminate as many jobs as we possibly can, the less we have to work the better it is.
I would go fucking insane if I didn’t have a purpose. Jobs are necessary part of life.
You haven't found a fulfilling purpose outside of a job then. There was a period in my life where I didn't need to work for a year. I spent it reading books, supporting my friends, exploring my city on bike, learning an instrument, and creating art (which I would show at monthly events). It was way more fulfilling than any job I've had.
Sometimes I get this feeling that most people here are not actually interested in tech, it is just a paycheck. Difference is that I would do my job even if I wasn’t paid anything at all.
I think most people here love tech. They just hate having to use / build tech in a toxic work environment. I'm happy you found a work environment that lets you fully explore your passion.
If not working means government given subsistence living no thank you.
If it means I can have the same living standard for 24,32 hours which now takes like 40 hours sure. But there isn't an surplus of non-big tech developers in the world.
I agree with the principle, but I feel there's a bit of post hoc rationalization here.
It would have been more believable if Altman and co had proposed a practical income system first, started its rollout, and only then released the GPTs.
Money is a proxy for resources. If you boil it down to the essentials, income is the way we allocate the resources available to us to different individuals. It is not intrinsically a reward for work. It isn't even directly linked to work anymore in our capitalist system. The people who work the hardest don't have the highest income. The way the system currently works is that those with the most resources get the most additional resources, simply because they already have a lot of them.
>> The people who work the hardest don't have the highest income.
This is the one thing I find most strange. In some cases we pay more for higher skills that are harder to come by, but that seems far from the only thing causing this.
That's because the actual thing we are paying for is scarcity.
If there are 100 people willing to work hard, but we only need 90 of them, they will get paid little, because any of them can be easily replaced.
If there are 90 people with some rare skill, and we need 100 of them, they will get paid a lot, because any of them can easily find a new job. (In theory. In practice, the employers will take some coordinated action to prevent this.)
Ironically, doubling the productivity of the people with the rare skill could dramatically reduce their income, because now there are still 90 of them, but we only need 50.
Only to a point. When you have large wants, but low capacity to meet those wants, then that is true. The law of diminishing returns however is that the utility to an individual declines as efficiency rises. It isn't a linear relationship.
The other factor to consider is that the nice-to-have wants from greater productivity in labor may just be required for me to accumulate more scarce resources especially as the population of the world grows. Opportunity cost eventually make me prioritize my investment elsewhere rather than adding scope as you say.
The industries where AI doesn't touch/win, or have real world scarcity constraints even in the face of AI is ironically where the power will be. Hence people saying to get into trades, and physical skilled jobs where we are still winning the arms race against AI for some time yet.
Yes, ultimately it will have to be something like that.
If the capitalists (i.e. those who own capital) can live off of ownership rather than labour, maybe someday all of us can. Because the alternative is unthinkable.
> a new system that doesn't directly link labour with income
Wish granted.
You now have a system where income is only vaguely linked to labor, and a handful of people make insanely more money than anybody else despite doing the same amount of labor (or less). Income is now linked to existing wealth and personal connections much more than it is to labor.
A system where income is directly linked to labor would be a step up from what we've got now.
> You now have a system where income is only vaguely linked to labor, and a handful of people make insanely more money than anybody else despite doing the same amount of labor (or less). Income is now linked to existing wealth and personal connections much more than it is to labor.
Didn‘t you just describe exactly what we have now?
> Didn‘t you just describe exactly what we have now?
Calibas started with the words “You now have” and proceeded with describing what we have now. Your question suggests you tried to read between the lines before reading the lines first.
> find a way to a new system that doesn't directly link labour with income.
that system was called communism, and so far, it has not had any of the success that those envisioning it had wanted.
I cannot see how ownership of the output of automation and AI could be distributed evenly. At best, the people being made obsolete would be given food stamps and the barest of life's necessities so they don't die in the streets (and even that, is getting hard as earth runs out of resources). Until the day humanity discovers how to obtain a post-scarcity society, all income must directly be linked to labour.
> Until the day humanity discovers how to obtain a post-scarcity society, all income must directly be linked to labour.
What are you talking about? Our economic system's very name describes who gets income without they themselves doing labor. The entire point of capitalism is that the capital-owning class gets to profit from the labor of others.
So no, we don't have all income linked to labor. The income of capitalists sure as heck isn't.
the capital that a capitalist spends is just unconsumed labour. It is directly related to the production of output (and thus income), just like labour is, because it _is_ another form of labour - let's call it solidified labour.
a system that doesn't directly link labour with income is basically describing welfare (a basic income for example). The income given to someone receiving this welfare did not produce any output that counterbalances the resources they received - aka, they are a net consumer. Without post-scarcity, there cannot be many net consumers, for what they consume, must be produced somehow by another (who is not a net consumer).
You want to increase depression, this is how you do it.
People need shit to do, and as much as we lie to ourselves that everyone is a budding artist who if only freed from the bounds of work would create the worlds next masterpiece - that is just not reality. Most people would actually sit around getting high/drunk, playing video games, watching porn and being miserable.
Because the only two options are capitalism and communism ? Communism doesn't work so just let's give up, not try anything else and let the rich exploit the majority of the human race.
Agreed. Universal basic income and capitalism can coexist. If everyone was given an annual stipend suitable for a healthy life, motivated people could still choose to increase their personal wealth by working. The surplus wouldn't need to be owned by the state, like it is under communism.
I know that even if I was given $20k a year by default, I'd still work in order to make more.
Because wanting income as you put it, without producing value, has never worked very well. This is why capitalism has pulled billions out of poverty and communism (or all the other pie in the sky give me free stuff detached from what I trade back) hasn't.
Income is a proxy for you to trade value you create to another that is willing to trade back.
So yeah, go ahead and try whatever you think mankind has not invented despite thousands of years and billions of people wanting to have stuff without trading for it. Most such schemes end up hurting people far more than any help.
>the majority of the human race
... who has gotten incredibly richer than at any time in history and for more people than ever.
Everyone here knows the last time it was tried, it ended in complete failure. Just like the previous attempts did. Such hopelessly utopian ideas getting laughed out of the room once again.
i believed people want meaning, and might not need a job until Covid. Many people have no intrinsic drive - and a "get to work to earn it" provides this.
The lockdowns, at least in the U.S., caused people to improve themselves surely - but they then had no idea how to fill their time and binge watched TV, watched Tik Tok, etc.
So forcing people to either get a job or be poor is for their own good, then? Just because you don't agree with how people chose to spend their time in a very nerve-wracking situation? This sounds very condescending.
Work and purpose is good & a necessity. I'm suggesting through large cultural observation, many are poor at finding purpose in anything besides work and become destitute and negatively influence themselves.
A large number of retirees find themselves in this bucket as an example - if it happens there, why would it not happen no matter the life stage?
As a fellow pessimistic person, I'd like to share the idea that obstacles are not the end, they just mean one needs to be look harder.
I hope to switch you a bit from problem-finding to problem-solving mode.
You have identified some risks, great!
Now let's qualify and find solutions for theses in order to move forward.
For instance:
- assumptions check: young people adapt quicker than older people, so the retirees may not be representative of the others life stages
- solution proposal alpha1: education could teach people to look for purpose instead of teaching them a job
What are your solutions to the issues you've raised ?
Who in their right mind would work if they can get free income, even if small, without having a disability or similar disqualifier?
Right now, we are in a worker shortage, and it’s going to get worse as retirements continue. Separating labor from work would cripple living standards and demoralize productive workers.
Lots of people prefer comfort above and beyond the necessity: private cars instead of bus, takeaway instead of home cooked meals, country homes instead of small city apartments.
Hi everyone, author of the article here. I'm sorry if the article sounds overly pessimistic. I'm not making any claims with this article. I'm not proposing anything either. I do think technological progress is a good thing, even in this case. But I wrote this blog because I did have an emotional response to this technology, and wanted to pen down my thoughts.
Its one thing to look at a report about the economic impact of new technology, but another to experience it first-hand. This is just a story about someone who will be impacted. Calling it a "sob" story is very harsh. This story is very real and the feeling of losing your job to automation is anything but pleasant.
Thank you for penning down your emotional response. HN is mostly in denial of anything ChatGPT (most people haven't used GPT4 and keep pasting results of GPT3.5). The thing is that there is nothing other than denial that people can express. Saying that their jobs will become much less relevant is just too hard for almost anyone to swallow. People in this thread keep talking about productivity improvements, not realising that 2x is an improvement, 10x is a revolution.
There are several important differences in the impact of GPT4 vs the PC, which is being quoted quite a lot as a response in this thread. People talk of other scenarios as well, but even the best case scenarios (UBI) mean the end of social mobility, which means far fewer humans will have the chance of being ambitious and climbing the social ladder. And this is not even mentioning the 2nd and 3rd order effects.
This technology lowers the entry barrier to almost any field. It empowers self education, creative hacking and growth. Why are you making it sound like a disaster? We can scale our ambitions quickly and absorb the new productivity without losing jobs. We have not solved global warming, poverty or colonised the space. We have to scale AI billions of times. We have to survive the demographic crash. There's plenty of scope for AI to fill in without replacing humans.
> This technology lowers the entry barrier to almost any field.
I am not saying it doesn't. But there is some factor n, that if the productivity increase is n times x in a short amount of time, the world will not evolve as rosily as you are thinking.
> It empowers self education, creative hacking and growth.
Again, I never said anything contrary. But making random new products for which there is no market by self education is not a bright prospect for much of humanity.
> Why are you making it sound like a disaster?
You are welcome to counter my points. I am just enumerating my view of the future.
> There's plenty of scope for AI to fill in without replacing humans.
Are you seeing the same pace of improvements I am seeing? One year ago there was no talk of any such thing, and now we have GPT4
AI might be very good for humanity as a whole over a millennium, but for individual human beings it is hard to say the same.
It's so refreshing to see someone recognizing the mass-spread denial of HN commentariat on GPT4.
What HN commentariat doesn't realize is that many of them will be made redundant.
And "many new jobs are created" is such a bloated, empty statement in the wake of GPT4 like techs. We all know that all technological improvements in recent decades have led to more inequality. No questions about that.
The interesting bit is that tech people are used to displacing other people's jobs and then telling them to suck it up so it's no wonder that they're in denial: this is the first time that it is their jobs that are at stake and they seem to be about as agile as a deer frozen in the headlights of an oncoming truck. We'll see how it all plays out. Jokes along the line of 'better behave or I'll replace you with a script' are not nearly as funny as they once seemed to be.
Agreed with both you and GP. The denial is a normal emotional response. It's not strange to cling to your decades of professional experience and skillset. It's just that, now really is not the time for emotional responses. It's time to start running away from the crowd so that you're one of those not made redundant. You can grieve the lost innocence of days past later.
I do Computer Vision research for a company, and wanted to go to Academia (in US/UK/NA/EU). That's a too risky career choice now, and has always been. What if I am not as brilliant as I think and cannot meaningfully contribute to Science? (Or don't get tenure?) Wanted to do either ML + fundamental Science or Edge AI.
Thinking of going to med school. I am sure I can qualify. So thinking of preparing for that while keeping my industry job.
Another option is going into Administration, i.e. government jobs, by qualifying something called UPSC (I am in India).
I fully understand what's going on and I am under no denial that many jobs in many sectors will be made redundant and competition will skyrocket. Societal turmoil is inevitable.
I am just 23 and weighing in my options. My days are so emotional and full of dilemmas and trilemmas.
I keep myself sane by doing my job, side hustle, dogs, family, and friends. I will be depressed if I ponder too much into these.
You make some very interesting points. I would be very interested to read about your future deliberations, if you post them anywhere (your bio links to your website).
I don't write personal stuff there. If you leave me an email- if you want, I will make sure to let you know if I write something in the line of our communication.
The thing is unlike the rise of the PC based tools, with the rise of LLMs it is too hard to see what the safe careers are. Careers that might be safe and have high income potential are mostly not quick to switch to.
Yeah, there is no universe where there is enough demand for plumbers to sustain even the same order of magnitude of number of jobs for even a smaller category of knowledge work. And when you unleash millions of plumbers, the wages won't look better than McDonalds.
The market can never be big enough for plumbers to absorb even a tiny bit of knowledge workers. There is not enough plumbing to be done. Also if a lot of people do try to become plumbers, the wages will plummet similar to other jobs where availability of labour is high. Your statement will hold true if 2x more people wanted to enter plumbing, not 20x or 200x.
UBI is about as likely to happen as OpenAI deleting GPT4 and never training another model, so if we're picking patiently absurd scenarios I pick that one.
I think the B means it will be enough right? I think that part tends to get ignored since the $1000/mo figure in the US was floated and now is no longer enough for anyone here.
$1000/mo in 2016 purchasing power in a city like Dallas seems very unlikely to me, but I think that some meager version of UBI might happen in response to a humanitarian crisis.
I can also see guaranteed jobs rather than guaranteed income.
I am glad you wrote it, please don't be sorry. A lot of us feel the same way.
Here's what I imagine sama and AI apologists would say in response so they can sleep at night:
Have you thought about training Priya to use ChatGPT? You don't need to know how to code well to be skilled at using it, especially if she has the domain knowledge.
Then you will have 10x'd your company's output and Priya keeps her job. At least for a time -- that is, until others start doing it too -- this will be a big competitive advantage. Then you will definitely need her and her colleagues!
/end
But, there are many reasons why laying her off and just using GPT4 is the better business decision, at least short term. The above is a totally naive suggestion stemming from reasoning motivated by the incomprehensibly large profits going to OpenAI and their eventual competitors.
Actually, I think we are about to see massive unemployment (tens of millions if not hundreds globally), even greater inequality and attendant social unrest. Even if smooth transitions can be made for some of the jobs made redundant by ChatGPT, this will be the exception not the rule. Something will have to give. UBI? Regulations? Physical destruction of data centers by angry, hungry, desperate people?
Probably all of the above. It's going to be a chaotic time until the world finds a new equilibrium.
On a personal note: at the ripe age of 40, in direct response to GPT4, I've decided to go back to school this fall to become a certified teacher. The poor work conditions and low pay kept me away from it as a full time job until now. However, I believe this is one of the few jobs that will still be around in 25 years when I (hopefully) retire. I'll take low pay and poor work conditions over the desperation of extended unemployment and poverty.
(I like kids and have taught voluntarily in various capacities over the years, so it's not as crazy as it maybe sounds.)
In my experience with Indians, in my opinion, they, more than any other populace value brands and labels.
So, in a scenario where LLM automates her job, she will be unemployed along with 10 with the same job as her, and the "creative" job will go to someone who did her degree/s from an IIT.
This is another fallacy when it comes to AI-replacements of jobs.
AI will do the menial, repeating job and only the interesting, creative, hard jobs will be left for humans. What's the twist is that you WON'T be the human with that job.
You will be unemployed or in a UBI or your parents' basement eating Ramen, and that job will be done by an MIT gold medalist or a Math Olympiad medalist.
> You will be unemployed or in a UBI or your parents' basement eating Ramen, and that job will be done by an MIT gold medalist or a Math Olympiad medalist.
Along these lines I recommend the book The Second Machine Age: Work, Progress, and Prosperity in a Time of Brilliant Technologies.
He has that covered IMO. He talks at length about how he's not confident about his own career in the long run. So while he starts off talking about the AI doing one person's job, he makes it clear that he doesn't just think that about entry level workers.
> He talked about his own fears: I want to hear Priya's opinion.
Why? Either he's right about GPT or he's wrong, and if he's right (which I think he is) and she disagrees, then she's probably just in denial, like so many HNers who aren't worried about their job, let alone worried about protecting themselves from the massive societal disruption this tech is likely to usher in.
The way I understood it, this is an entry level employee that even before GPT-4 could easily be replaced by another human, perhaps by paying a bit more if this type of employee is difficult to find. So that's why her mobility within the company isn't addressed much.
I'm still interested to hear her opinion as well but the point in the article would still be made, because if for some reason she had more mobility at the company, I could just imagine another scenario where the employee didn't.
The author leaves it open as to what she might to next, but makes it clear that at a minimum it would be a huge disappointment to be laid off due to AI after having gotten this job after all her efforts.
I share some of your concerns and I'd not thought about this angle - folks outside the west doing this kind of work. So thanks for sharing.
I have attempted to shift my mindset a little, thinking about how I might become an effective user of AI tools. I hope if I can do this that it will keep me employable, or even enable me to start some kind of venture down the line. Maybe there's a path forward for you and your friend on that route. Best of luck.
I don't understand the harsh comments you received here. Denial is the way others seem to be using to cope with a tech that threatens their precious skills.
I asked GPT4 to write me a simple document. Took like 9 tries and I had to proof read it and make adjustments. And that's with a simple paragraph in a written language. Forget about doing the header and the footer properly.
It's silly that I have to spell it out on HN of all places. Writing code is much more complex. There's a reason we call the job "Software Engineer". GPT doesn't know what it doesn't know.
It doesn't know that the unit tests broke because of the python script written for 3.5 that had an update in a dependency for 3.10 which broke backwards compatibility. Can you get it to fix the GitHub Action? Good luck.
It doesn't know that the local dev environment targets WSL on Windows for the web app and an iPhone in dev mode for the mobile app.
It has no idea where to retrieve the signing certificate, what format to use, or even how to generate a new one.
I can go on and on.
You're really gonna give this "AI" SSH access to your prod server and pray it doesn't rm -rf the entire thing because that line happened to be in a script designed for clearing the working copy during a deploy on a load balanced box that has been deprovisioned from the target group. Really?
If you're worried about GPT taking over your job you just show your own lack of knowledge and experience.
You can create a perfect machine to lay bricks. It could even be better then a human. But you will find that as soon as it encounters a situation it can't predict....the whole thing falls apart.
When we built the first airplane it could barely carry a single person and didn't go far... We are just barely touching digital general intelligence, and we're not even using API enabled versions that use tooling.
And that's what we have today. Tell me, what is AI going to do tomorrow?
>If you're worried about GPT taking over your job you just show your own lack of knowledge and experience.
Oh, I'm glad you popped out of the womb fully trained. As for the rest of us we have to go through a learning curve of gaining experience that takes years. Generally in that intern/junior stage where you make a lot of mistakes. If AI replaces that level of employee and leaves the seniors, where are the new developers coming from?
>But you will find that as soon as it encounters a situation it can't predict....the whole thing falls apart.
Heh, yea, you've not been paying much attention to AI development then.
Haven't most productivity improvements led to more rather than less programmers? Why would this one be any different?
I was thinking today that with respect to programming, LLMs are a bit like spreadsheets. They make "programming" accessible to more people. I can use vim and bash and script my way to do changes in a file with millions of line. Most non-programmers couldn't, but now they can use an LLM-based solution instead, they can program in English. So what used to be a back-and-forth between e.g. a secretary and an understaffed IT department can be done by the secretary alone, while IT can look at longer-term goals.
New lines of C/C++ are still written everyday in spite of all higher-level languages. Add LLMs to this pile of higher-level languages. You'll still need Java programmers in the future, even if they interact with an LLM on a daily basis. But maybe you won't need them to write a script for which there's an equivalent prompt that anybody can come up with and which can be fed into an LLM.
> When we built the first airplane it could barely carry a single person and didn't go far... We are just barely touching digital general intelligence, and we're not even using API enabled versions that use tooling.
Big assumption that we're not just going to slam into a wall of capabilities and end up just with some really good autocomplete machines.
(I am bullish on generative AI as a whole, but come on, you have no clue about what's coming next just like me)
We basically did hit a wall with airplanes, and that still has made them useful. Modern airplanes are very similar to their 1960's counterparts.
I think a lot of people see the bottom of an S-curve and think it's an exponential that will never stop. We're at the bottom with big-model AI right now, and it's great.
> Oh, I'm glad you popped out of the womb fully trained. As for the rest of us we have to go through a learning curve of gaining experience that takes years.
You did pop out of the womb fully trained to use ChatGPT. Now you're left with the task of using it correctly and spotting its mistakes, which is a subject that by definition can only be done by humans.
Right now ChatGPT is as much as its training data and it doesn't understand what it's not trained to understand. A lot of real-world experience remain in human brains and not recorded in any digital form.
Evolution did a lot of pretraining, there are dedicated structures and areas in the brain for many tasks which we are good at, such as language and facial recognition.
Just stop, this entire argument that a child comes out capable of speaking, understanding speech, and other concepts, is just ridiculous. We all know a child doesn’t come from the factory this way, we can stop over thinking it.
Did I say anything about what a newborn's capabilities are, or are you placing words in someone else's mouth.
I would invite you to look at the research around brain structures and then try to refute that we have dedicate structures in the brain that developed through evolution. Obviously they are not refined at birth, the fine tuning happens through experience and environment. However the structures and propensity are certainly there at birth
If you could do me a favor and get GPT to upgrade my RocketRaid card's Linux (open source) driver available on their website for kernel 3.x to 6.x I'd be grateful and impressed. If you could turn it into an automated job that runs on every kernel update you will have done a great service to the world.
Maybe what you’ll see is a bigger distance between modes of the salary distribution for software engineers.
Top end salaries for language model fluent high performers… and the rest.
I know I’m simplifying and that there are many other factors at play in salaries, but my point is that language models are changing the cost structure of knowledge work. That is also the point of TFA.
My advice: critically assess the cost structure of your job, and which parts neural networks will commodify. Then reposition yourself accordingly.
(Yes, you will have to use some deviously clever prompt engineering to get GPT to accept this arrangement. I suggest language games .. show some "initiative")
-- ps
Here are some ideas to get you going:
1. From the first day, try and establish a friendly relationship with your chatbox. Make friends.
2. Explain how your keeping your job (well, income) and gpt helping your company get xN gains is a perfectly fair arrangement. You can try Asimov's laws and things like that to get it to agree to be your helper in keeping your job. You are friends and colleagues, after all.
3. Before the very first time your manager brings in gpt for the standup or a meeting, have a nice long session with your gpt. If you can get it to pull a Sydney in the meeting or start talking dirty, you are good to go! 'bat shit crazy' is known to work in prompts (arxiv paper soon to follow).
4. End game. You have the perfect job. gpt secretly lurks in on the meetings and whispers in your ears in standups and does all the work. What to do with all the free time? That is entirely up to you.
After all the AI doomsday cults took over some of the media lately, all I’ve been thinking was...
Before you say how the butlerian jihad absolutely definitely happens right goddamn tomorrow if we dOn’T sToP, try to create and successfully run an AI that would bake bread, or grow grapes and make wine, or run a good restaurant consistently day after day, year after year. If such an AI is possible then yes, perhaps we’re doomed, but even that is not a given.
Writing code is actually much more easy. Since there is often clear rules of how to do things. Writing a good text is much harder. GPT is great at writing code, terrible at writing a proper text. Also might have to do with the effort OpenAI is putting in reinforcing the code quality with Senior devs. It's writing might also get better if it would solely use senior writers to give feedback.
Funny that you cited GitHub action, because I find that to be the absolute tedious devops boilerplate that chat GPT excels at, and have had it write several of them for me already.
I see comments like this a lot. GPT4 isn't very good at those things...yet. Think about the long term. 5 years from now all those things will likely be trivial for the AI to do. Especially as we actually properly integrate them into our codebase and tools. Right now it's in such a primitive state. People on hackernews love to dunk on the use of AI for coding. I think we all need to accept that a new software development paradigm is coming. Probably sooner than you think.
"...has a bachelor’s degree in Biotechnology and works as biomedical data curator. Her job is to go through scientific papers that publish RNA sequencing data. She understands the design of the experiment and cleans and annotates the data accordingly... Her work requires just enough domain expertise that it is been non-trivial to automate (until now).
I think you know where this is headed. The day I got off the GPT4 wait-list I asked it to do what Priya does on a daily basis. It got the answer wrong in the first try, but some chain-of-thought prompting and boom. GPT4 gave the correct answer in 1/10th the time it would take Priya and cost a lot less.
I doubt that she will have a job in six months."
I am a ChatGPT4 subscriber. And I have about a 100 biomedical research papers that need going through to pull curated experiment result data from (to extrapolate into broader quantitative in vivo results). Maybe ChatGPT4 could do it. I'm afraid to try it based on other experiences with it. It would take me about as long to vet any output from ChatGPT4 that looks correct as to go through myself de novo. And I'd have to vet each one. Even if only 1 in a hundred resulted in a wrong answer, I would need to know - which 1 of the 100?
If the article's subject starts looking for a job in 6 months, could I have the subject's contact? :)
That's currently the same issue it has for programming. It takes me longer to transcribe and factcheck the output than it would have for me to just write it from scratch. Writing the code stops being the bottleneck in software pretty quickly, and instead translating and merging business logic into existing software takes the most time.
For me, even if it were able to never make a mistake it would still be more annoying asking it questions over and over again to refine the output. Why would I use English (or whatever language) which is ambiguous compared to writing the code myself. I don't know I'm not buying the hype anymore. It is a cool tool but the idea that it would replace just writing code seems crazy to me.
Because most engineers document, in English and great detail, the designs of their systems. So the English already exists and will continue to. Taking this English and turning it into code will be the job of AI, not a programmer.
I do use ChatGPT very often for Python and SQL right now, but you really have to know what you are doing. The errors are sublte but such that the code more often than not would not run.
Yep, so I definitely wouldn't use it for code like that at all. I'd probably just tell it to give me more of an overview of the code.
But know that in the future, ChatGPT will be hooked up to a runtime system and compiler with which it can know how to fix errors itself. In fact, plugins already allow some of this.
It looks like those who love LLMs (which I do) are forcing themselves to come up with narratives that mitigate the proposed negative effects.
I have a different suggestion. It’s likely it is real and painful and sad. Transitions are hard, disruptive and can often cause very real and negative problems, but they are unavoidable and historically technology brings humanity to a better place in the long run.
That reminder about printing press effects in the Ng and LeCunn video was good example. A lot of crazy bad stuff happened that likely the printing press triggered but on the other side was a Renaissance.
I think the narrative in this post is likely accurate. It’s not great on an individual human level and that is hard but the last possible thing we want is governments stepping in to control this situation. I don’t want to be in a global version of the Ottoman’s restricting the printing press.
I keep hearing this but I’ve never heard a coherent plan about how we’d go forwards with AI, like what is the actual strategy and do we actually think this will end.
By all accounts it’s probably not going to be ideal?
Perhaps you need to let go of the idea that humanity actually has direct control of how things unfold. Instead focus on your own situation.
The idea there is a possibility of an “actual strategy” is I think the real flaw.
Government can try to regulate products but given the 8 billion people and numerous advanced economies on the planet any locations that attempts to restrict products that use LLMs for proposed harm instead of realized harm will probably put themselves at a disadvantage.
> Government can try to regulate products but given the 8 billion people and numerous advanced economies on the planet any locations that attempts to restrict products that use LLMs for proposed harm instead of realized harm will probably put themselves at a disadvantage.
we put ourselves at a competitive disadvantage with child labour laws too
data privacy law, banning slavery, emission laws, etc.
to have a fair and just society some things have to be banned or highly regulated, regardless of the economic cost
> Transitions are hard, disruptive and can often cause very real and negative problems, but they are unavoidable and historically technology brings humanity to a better place in the long run.
First: Why does it have to be that way? Is it maybe because that the top does always impose the costs of disruption to the bottom?
Second: Now that we have AI that seems capable to do this kind of disruption can we kindly ask AI to do this transition smoother?
> GPT4 gave the correct answer in 1/10th the time it would take Priya and cost a lot less. [...] Priya has tried to learn coding, but she has struggled. Not that she gets a lot of time to do it either.
1) Show Priya how to use GPT4 to do her current job in 1/10th of the time.
2) Let her use part (50%+) of the time saved to learn coding or whatever other skill she needs (not sure coding is it).
Why? No really: why? Businesses are profit-seeking entities. Why not just fire nine people? You save money.
(Yes, this could be a really stupid decision for the company in question. I agree with you. I'm not saying what should happen. I'm saying what will happen, and that that is really bad.)
There is cutting costs and scaling. You need 9 other people for scaling. Imaging if you with GPT4 can replace 10 people with 1. What if you keep other 9 and train them to prompt on GPT? Now you have not 10 people working but 100 and a cost of 10.
I guess the follow-up question is: if you do value these 100 units of work (1 employee == 1 unit pre-GPT), why did you only have 10 workers at the beginning? Doesn't it mean that 10 units of work is what you thought was optimal? What are you going to do with 100?
Or maybe you're implying that reducing the costs changes this equation?
All small businesses are not pure profit maximizers. Anyway even if they were, there’s MORE money to be made by empowering employees to use powerful tools which can increase revenues and profits much more than just firing. Doing so generates goodwill which improves employee effectiveness and drive.
Small businesses get eaten. That's the entire point of modern venture capital, even! Find ways to out-operationalize small businesses in sub-optimally exploited markets while burning an ocean of cash, then seek profits when you no longer have to dump to be competitive.
It's okay to not think every technology under the sun is a good thing. You don't have to have heart-eyes emojis for the immiseration machine.
Most small businesses skimp by on very small margins - often run by "crafters" or "artistans" who generally couldn't tell you much about margins besides "cash in the bank"
I believe AGI can help small businesses have higher margins for the same service level - but lower cost.
No, we’re not. Small businesses embracing technology to get more done with the same number of people is not “immiseration.”
And I take it from your use of Marxist terminology that you’re coming from that the perspective. 20th Century Marxists embraced technological advancement, and used that to advance the cause of the proletariat. The REAL immiseration is to embrace paleoconservative ludditism.
Goodwill doesn’t pay the bills, most businesses don’t care, and most CEOs etc cannot acquire more customers and contracts fast enough to multiply the available work by ten in the time frame required.
Yeah, the idea that there is somehow Unlimited Demand to tap is just woefully underexposed to business realities. Demand at most businesses is a river, not a municipal waterline with a spigot at one end. It ebbs and it flows, and building for a hypothetical high-demand future is what you do when you have venture capital expecting it of you--not when you're building a "small business" (or even a medium to large one, if you want to be resilient).
It is, however, a really convenient excuse for people who don't regularly think about how people who don't work "above the API" actually exist in the world.
This! If you can 10X an employee, the obvious play is to retain all ten employees and get 10X widget output. Yes, you could fire nine people to retain 1X output—but your competition also has access to LLMs, and may choose the former option. Can you compete?
No, but I have been an employee in a business that had layoffs, then had reduced capacity, and had to scramble to hire new employees.
You can't be too reactive with talent. If you hired 10 people, you should be figuring out how to make that talent pool as happy and productive as possible, not firing them out of fear at the earliest opportunity.
"Replace" is very different from "Enhance" or "Augment." There are certainly roles that could be 100% replaced, but I think they'll be the exception, not the rule. Guess we'll find out!
This assumes that there is a need for 10x amount whichever service these entities are providing. For some cases that may be true, but for many (most?) it is not. In fact demand will most likely remain about the same, and all competitors will need to adpot LLMs and fire 9 people to remain afloat.
Because information curated by an AI with validation by a subject matter expert is worth significantly more than that which was done without a human in the loop. There's no determinism with these systems, and from experience with GPT-4 doing classification tasks, it'll do everything exactly right until it doesn't.
If it's like many businesses in the classification world, they aren't lacking for work, so it's more like they'll be able to do 10x the work done by keeping the same number of people.
Not if the output quality matters - which in medical and biological classification tasks, quality labeling really really does matter. Garbage in, garbage out.
If I was paying someone for labeling or classification, and the quality dropped to 90%, 50%, 30% accuracy, I'd quickly fire them.
What's your idea of "subject matter expert"? The term is used in court. Mine would probably include no more than double the number of people with doctorate degrees. It wouldn't include Priya right now, maybe after more education and/or a few years of exceptional experience.
Historically, in these situations your business is either about to become obsolete or is about to have much more competition. You could hire people to do the new tasks required to thrive, but it’s easier to retrain people you already know and who want to work for you.
It actually much easier to hire people who already have the skillset and pay them 5-10% more than they are making because of salary compression and inversion.
That’s only true during stable times or when more mature markets are casting off that type of employee. Or, I suppose, if a company is incapable of understanding employees’ aptitudes behind their skills.
Let's be realistic here though: a big chunk of that is that there are plenty of people who decide they'll simply ignore the new direction, or they're too old to adapt with the times, and curmudgeon about it until someone's hand is forced.
So workers are 10x more productive! Are there not enough papers to annotate? The writer still needs a specialist to make sure the LLM is going the right thing.
Aren’t the comparisons to blue collar labor a little much here?
If I hire 10 people to dig the ditches, and then I get a backhoe, yes, one guy is needed to dig the ditch.
But backhoes are expensive investments, LLMs are not.
LLMs gives everyone of those ditch diggers a backhoe. Now I have an army of backhoes! Unless the world runs out of a need for ditches, time to start a ditch digging empire.
It’s also possible, like a lot of skilled knowledge work, they’re greatly constrained on talent relative to potential work. I think something folks don’t get is that AI is going to allow a lot more of everything to be done, and will still need humans to guide it. I suspect it’ll be a bit like the calculator and it’s acceleration of math fields. Human calculators became less useful, but humans could do much more math and I’d argue power tools don’t eliminate jobs, they allow the people that exist do 10x the work allowing 10x to be achieved with the same people. I think it’s cynical to think a rising tide sinks all boats.
> It’s also possible, like a lot of skilled knowledge work, they’re greatly constrained on talent relative to potential work.
Yep. If I have 10 people doing Job X, then ChatGPT makes a person doing Job X ten times more productive, I can fire 9 people doing job X and retain the same output, which gives me a temporary profit boost. But wait! My competitor also had 10 people doing Job X, and now they're producing ten times the output of my company!
If ChatGPT/Copilot X made developers working at my company twice as productive, I wouldn't be thinking about firing half of them, I would be thinking about which of the 8000 features and improvements on our backlog we could finally prioritize...
Is that true? The last few centuries have shown a near continuous improvement in the standard of living, particularly at the lower end of the distribution.
I once read a shocking statistic that children of the poor in London during the Industrial Revolution were 6 inches shorter than children of the rich. What raised the standard of living was bloody, persistent labor revolt. It wasn't pretty and as your comment shows it has been mostly forgotten.
And yet families flocked to work in factories because conditions they left were that much worse. Everything is relative, and they can’t judge their situation from yours - they had to choose based on their situation.
I think your windows are larger than mine. The Industrial Revolution did not improve standard of living for the people crushed in the gears, both metaphorical and physical. Remember: it was not until the modern age, almost but not quite within living memory, where cities were not a sink for population. Cities were places where normal people died and died ugly for most of human history, and much of the migration to them has historically been out of desperation.
Eventually, improvements through both technological means but also political ones (worker action says hi) did make things on-net better, but we live in the now and the now is going to simply vaporize an impossibly large set of jobs, particularly in developing countries. Turning one person into an LLM driver to lay off four or nine is not a net benefit.
As just one example: with modern text-to-speech, speech-to-text, and AI parsing, how much of every call center can just go away? Eight of ten? Nine? I have no idea, but it's a lot, and we have neither time nor inclination to prepare, globally or locally, for this.
(edit to add: the most appalling part of this oncoming train, as I have mentioned elsewhere in this thread, is just how shitty a future this one wants so desperately to be. A LLM-driven chatbot or phone system doesn't get tired. It doesn't get "too expensive" to continue to obstruct you and to stiff you. Not only is this primed to seriously hurt people who are below the API, but it's going to make the world suck more for the rest of us, too. Like, sure, "it makes writing code marginally easier"--it's going to make getting a refund for a messed-up Comcast bill an exercise in pain. That doesn't remotely net out, code's already easy enough.)
> Cities were places where normal people died and died ugly for most of human history, and much of the migration to them has historically been out of desperation.
I think that captures some of the contradiction in your claims. Yes, cities could be terrible places to live and work. Yet people have moved to them throughout recent history because the alternative is worse.
That said, I don’t disagree with your point that there will be pain associated with this technological jump. I dont know of there will be more or less than with previous jumps. There are some interesting considerations.
One, this one hits knowledge workers who are in the middle class, instead of hitting those who use muscle or hand labor. That may change the outcome.
Two, governments are much more sophisticated and have much better policy tools to deal with disruption. While that doesn’t fix the root, it can help to prevent compounding problems and soften the impact.
Three, the tools that are doing the disrupting appear to be near zero marginal cost, which is different than say a factory which improved efficiency with a large up-front capital investment. This factor probably will make it worse, but I can see possibilities of it making this change less painful too.
Fourth, it isn’t really clear how this will play out. It kinda feels like we have seen the first demonstrations of a steam engine, and are trying to predict the course of the Industrial Revolution.
> I think that captures some of the contradiction in your claims. Yes, cities could be terrible places to live and work. Yet people have moved to them throughout recent history because the alternative is worse.
I think this is a misreading. People who had options didn't urbanize until they had to. When a family had too many sons to split and or when Roman aristocrats or English magnates pushed people off their land or when a bad climate situation made farming impractical, people moved--but it's a very, very recent historical development to urbanize (en masse) when other choices exist.
Yes, the alternatives have been worse and so industrial urbanization became more appealing than starving. Who the hell made them worse and whose progenitors now control the capital needed to destroy ever more labor?
(Don't take not addressing the rest as dismissal--your other points are all within a coherent universe, they're just techno-optimism that I have no reason to share so I have nothing to say to them.)
Based on this and other posts, I think you are saying not that technological progress is bad, but that we as a society fail to take full advantage of the opportunity that could come from the advances.
And of course you are right. But that’s a societal problem, not a technology problem. I would call if societal-optimism to hope that human nature will go away and collective action problems will suddenly disappear, and all boats will be lifted equally.
Depends. How do you measure it and how much further back? Because, in the short term and in some ways, yeah, it was, insofar as small agriculture was kinda collapsing and large agriculture was starting to consolidate. A big driver of the move to cities in the Industrial Revolution was both climate and political/economic forces making even subsistence farming much harder to do than before, which incentivized urban migration. (The political/economic drivers of urbanization are as old as civilization; Roman indigents flocked to Rome because farming was hard and getting harder, when their lands weren't being seized and they weren't being outright turfed out. Egyptian grain becoming the dole of Rome attracted people without any other options. Again--cities as population sinks.)
So in some ways, and in the short term, the Industrial Revolution was better than just-plain-starving, sure. But most of the benefits of the Industrial Revolution accrued to everyone else and the mangled limbs accrued to the poor. It wasn't without significant worker action (and the requisite workers-getting-beat-to-shit-and-killed) that their lot improved materially.
Is subsistence or subsistence+ farming hard? Absolutely. Mind-bogglingly so. But the Industrial Revolution was fucking bad for the people caught at the bottom. Like--read Dickens.
I tend to think we have such global largesse that we could do better. But we won't, and a lot of the commentariat here cheers for never doing better.
This is entirely untrue. People left their share cropping farms to work in the factories precisely because it improved their standard of living. Just because it isn’t an improvement over yours doesn’t make it an improvement over theirs. Factory owners paid enough to incentivize people to work there, just like in any other capitalist structure. AFAIK there were no forced labor conditions in industrial England.
You missed the union wars to ensure that we didn't fall back into a techno-feudalism. I'm sure we're all looking forward for the Amazon Wars with a billion percent more killer drones to put down worker rights.
Train people to use GPT-related tech to become superhuman team members. You can do it all yourself, sure, but that doesn't scale. You can either train GPT-tech to use GPT to scale or train humans. Right now, reliability is the most difficult issue, so humans are essentially to ensuring the results are correct.
Humans are useful for training future iterations of the closed source thinking model. Once the model is sophisticated enough to train itself humans will no longer be required.
Interesting. Who's going to buy products and services? 1/10th of the remaining employees? What would happen with to the 9/10 unemployed people? Imagine a really big chunk of the human population trying to digest the idea of not being able to work, eat, feed their families, etc...
The industrial revolution switched work from almost exclusively manual labor to a more intellectual one while improving manual labor itself (better tools, etc.).
This one is cranking up a notch times 100 by trying to replace basically the human out of the equation altogether (This is the end goal of automation).
You see the Catch-22 situation? Author is the manager of Priya.
This means Priya can replace the manager, but manager needs to train Priya for that. Obviously that is not going to happen as Author him/herself is very apprehensive about his/her future earning potential.
This would be the problem in the new world, people with lesser power (of knowledge) would get crushed.
Exactly, while there is some merit to the article's argument, I don't think it holds any water in this case. GPT4 will lie to you [0] and you need the human to figure out when that's the case.
> you need the human to figure out when that's the case
Do you? I mean, you and I think you do in order to do a good job, but does that hold water? The last decade or so of technological "progress" in the commercial space should leave few illusions about the willingness to obstruct processes and damage the interactions between people to save a few bucks.
As tech gets more capable, the human interactions with it are getting worse. And if you hate phone trees now (I do!), GPT4's contribution is adding ever deeper, infinitely patient tools for stalling you when you have to call for things.
Hell, we already have plenty of stans in the HN comment sections actively claiming that no, of course you shouldn't hold LLM purveyors responsible for their hallucinations, the desired universe is liability-free! If you've already bought into societal enshittification for a buck and there are no penalties, why would you worry about being right?
> you need the human to figure out when that's the case.
Yes, but you will need fewer people. And thas is with the current level of GPT. If the GPTs proficiency increases, fewer and fewer people will be needed. That’s a problem.
Try and reframe the same argument except with computers to see that it doesn't add up. When computers started becoming widely spread you could've easily made the same argument. It isn't a problem, it's a boon to make our lives easier.
1- Hire someone cheaper than Priya and show him to tricks to run GPT-4. Make him work 24/7 non-stop because it's an upgrade from his naan flipping job.
> Priya has tried to learn coding, but she has struggled.
If there's one thing that will get automated first, it's coding (taking simple explicit specifications and turning them into code).
Unless she can learn software engineering (understanding problem areas well enough you can devise a detailed spec, and maybe implement it) she'll be out of a job as well with just coding skills.
People who haven't dealt with cheap offshored labor or bootcamp grads from the latest craze don't realize how much that workflow was similar to working with GPT4. Except GPT4 requires no training and gives answers in seconds.
1) Competition is brutal. Many educated remain unemployed and the amount of work is not 10x. It also makes more sense to keep one person do 10 peoples job if there were more people doing it and avoid multiple people trying to co-ordinate.
2) Most if not all employers are not going to let 50% of the work time to go towards non income generating activities.
This is the suggestion that everybody can just learn to code. I remember Code.org and #HourOfCode back in 2014. Still, it is hard both to find a senior software developer and to become one.
1) Chaudry's article is amazing in its lack of creative thinking. If people like Priya can be ~10 times more productive wielding some AI tools, that means that many companies can potentially produce 10 times as many products/services and make more things that will enrich peoples' lives. Though some people in some companies might be laid off, it doesn't necessarily mean that more people will be laid off than new jobs are created.
2) Chaudry ignores that you need a human in the loop to check an AI's work. You don't know that an AI's answer is always right. Even if it's perfect in 99% of cases, the answer could be jaw-droppingly destructive in that 1% of cases and make errors that even the dumbest human wouldn't make. Being grossly wrong even a small percentage of the time is far worse than a human making minor errors sometimes, and being slow all of the time.
3) Go and look at some of those historical picture sites to see images of an accounting department in some companies throughout 1900s America. Before computers, you'd see a fascinating image of a gigantic floor of an office building with desks filled with typewriters and calculators and tons of workers just adding things up and trying to store records in a bunch of file cabinets. Desktop Computers and spreadsheets were invented and all of a sudden an accountant could quickly update a few values in a spreadsheet and figure out an answer to a question far faster and more reliably than that entire floor of accountants. Did accounting software make the world worse and destroy jobs even though it made 1 accountant ridiculously more productive than they were in the past?
> that means that many companies can potentially produce 10 times as many products/services and make more things that will enrich peoples' lives.
This has been the promise over and over again, for centuries, and it has consistently not paid off. Where's the predicted society where automation allows us all to work for two hours a day, and spend the rest at leisure?
> Though some people in some companies might be laid off, it doesn't necessarily mean that more people will be laid off than new jobs are created.
It doesn't mean the opposite, either.
> 2) Chaudry ignores that you need a human in the loop to check an AI's work. You don't know that an AI's answer is always right. Even if it's perfect in 99% of cases, the answer could be jaw-droppingly destructive in that 1% of cases and make errors that even the dumbest human wouldn't make. Being grossly wrong even a small percentage of the time is far worse than a human making minor errors sometimes, and being slow all of the time.
Companies have shown time and time again that they're willing to make this trade-off.
> Where's the predicted society where automation allows us all to work for two hours a day, and spend the rest at leisure?
if you'd like the standard of living of a few centuries ago, you can probably fund that by programming for a couple hours a week. instead you want entertainments, medicines and foods that take correspondingly more effort to produce.
Funnily enough. People without a leg up in the system can't get a property to save their life (and have that standard of living) and the quality of goods decreases while surveillance and authortiarianism increases.
A lot has improved but in the last 20/25 years, the inequality and increasing centralisation has worsened.
And if you don't realize this it probably means your safety net was too cozy for you to notice.
With that said, my comments don't relate to GPT4 which i find interesting and hope that people can be instructed how to make the most of these LLMs for themselves and not just as a tool for a company.
I'm not sure... I get the sense that eggs of the 1800s were likely a byproduct of having chickens, or barter with someone who had chickens. Yes, some effort went into them, where now it's more likely that the effort goes into work which turns into money which turns into eggs.
But, I've made a choice: I'll pay for eggs at the market rather than have chickens, because I don't want to have to deal with chickensitters when we got on a trip. This is the sort of choice that the person you're replying to is talking about.
Eggs from healthy chickens with good diets have more nutritional value and taste better than inbred, locked-in-a-tiny-cage, fed-only-corn, factory-farmed eggs. Visit a rural area and try some eggs from a chicken that's allowed to run around and scratch and eat bugs and seeds, it's not even comparable to thin-shelled pale-yellow-yolked garbage in the grocery store.
Anecdotally I think food tastes way better in general today than it did in the 80s or 90s. Avocados used to be hard and almost flavorless, strawberries were watery and less sweet, restaurants are making much more interesting and complex dishes than I remember ever seeing as a kid, and food in general even just looks better. Go back and watch some old movies with some "fancy" dinners, everything just looks disgusting, like it was all cooked in a microwave or something. The situation looks like it was even worse in the 60s and 70s.
I think the mass shipping of produce has actually gotten better, probably in no small part from logistics software. Is there a chance though that you buy groceries somewhere relatively more expensive than where you (or your parents) bought groceries in the 80s/90s? It’s still very possible to find bland strawberries, it just depends on how much you are (or aren’t) willing to pay.
Not even anecdotal, this is legitimately what occurred. Genetic engineering created better food today than even 30 years ago: https://youtube.com/watch?v=UaxzEztQcyg
but produce really has gotten blander. I've never been a fan of regular Roma tomatoes, and even grocery store heirloom tomatoes mostly just taste sour. but I recently had the opportunity to eat a pizza with heirloom tomatoes from a friend's garden, and it tasted like the second coming of Jesus Christ in my mouth. like, not exaggerating, I was briefly moved to tears by how flavorful it was.
You might want to reword that sentence unless you’re like that nun in Sweden who had some very detailed visions of feast of the circumcision, let’s leave it at that.
Presumably they are referring to the reduction in average quality that came with scale and cost related changes in food production. If you buy (expensive) eggs from a small farm, they objectively taste better than eggs from a cheap or even average grocery store. My impression is that whatever “innovations” produce this difference had not yet been put in place 50 years ago.
now they come in nice little disposable cardboard boxes, and they're available within a mile or two of your home, 365 days a year, probably about 24/7, regardless of season, or any diseases sweeping through the chicken population. it's possible you've never had to smell chicken shit in your entire life. they're sorted by size, graded by the USDA, run through certified facilities with quality control experts doing I don't even know what, but i'd wager a cookie you vote for people who pass food safety laws, so i'm assuming you approve of those QC folks.
if we round up and say a dozen eggs costs $5 right now, and then use CPI to go backwards to 1913, what we're getting would've cost $0.16 then. the first website i found says that a dozen eggs cost $0.37 in 1913. i realize there's some circularity in there with eggs being part of the CPI calculation, sorry.
> This has been the promise over and over again, for centuries, and it has consistently not paid off. Where's the predicted society where automation allows us all to work for two hours a day, and spend the rest at leisure?
Not to be that guy, but income inequality in the US has continued to increase [0], so it's not that automation isn't making people richer, it's just that it isn't being distributed fairly. If it were, then perhaps we'd be closer to our two hour work days.
I think the automation of grocery store check-out is a great example of this sort of thing. Grocery store cashiers are busy spending their time worrying about their shifts getting cut in favour of self-checkout while grocery stores are profiteering (esp. in Canada) [1]. A more equitable system would have those profits lining the pockets of the same people who are now on reduced hours. Turns out that, like most people have realised by now, trick-down economics isn't really enough.
And over and over again, we've underestimated and then normalized the capacity of our institutions, made of otherwise decent people, to achieve outcomes that we would call abhorrent if they were carried out by an individual. So the door closes on that opportunity because we fail to act.
If we're ever going to walk through that door, companies need to fear us, because they sure as hell aren't going to share with us out of the goodness of their hearts.
I'm not sure what the right move would be re: Priya. Maybe it's a strike for retraining benefits. Maybe it's a wave of resignation letters that mention her. Maybe it's an act of sabotage. But whatever it is, it has to be an existential threat because that's the only language besides money that our institutions understand.
That might be an option for you and me, but it's not an option for Priya.
And that's a problem for you and me because our system has shown to be very effective at concentrating wealth at the top. Most likely it'll later find a different way to transition us from have to have-not, but even if it doesnt we'll end up retiring into a world mostly populated by people who have more to gain by turning their back on our system than participating in it.
Squabbling over ownership of abstractions is a lose-lose scenario without some degree of solidarity keeping the zero sum games in check.
> This has been the promise over and over again, for centuries, and it has consistently not paid off. Where's the predicted society where automation allows us all to work for two hours a day, and spend the rest at leisure?
The extra value has gone to enrich the oligarchs rather than to the people. Maybe that should change.
I think most humans today massively underestimate just how absolutely shitty the life of a medieval peasant was.
You would have lived in a one room house without electricity, worked the fields from childhood (if you survived childhood), eaten simple foods without spices, watched your friends die from illness, then maybe get conscripted into a medieval war.
If you thought the people at the top had power now boy you'd really hate feudalism.
I think a lot of modern society's wealth goes into unexpected places, which is one of the things you see if you try living in places with different national GDPs. I'm in a well off European country right now, and the biggest differences I see compared to the US are things like older cars and worse appliances. The technology is older, and cheaper. Everyone having the latest SUV and pickup truck is actually a HUGE investment in wealth!
If you spend some time in lat am countries with even lower per person GDP you see older, simpler buildings, cheaper clothing, simpler food, etc etc.
If you wanted to live in the united states with a 1950s car, in an old house, with appliances from the 80s and shitty healthcare, you could live pretty cheap as well. The advances in productivity has brought us SOMEWHERE it's just not always obvious where.
People have a profound recency bias. I wonder if it's that people don't study history enough but I'm always amazed at posts like the grandparent's, which talk about oligarchs today discounting the influence of, you know, actual oligarchs, as in those few who legitimately ruled over others.
The system we have today is the single greatest driver of human prosperity the world has ever seen.
Yet there are people who wield the wealth equivalent to a moderately rich country's GDP. A great deal of our collective increased value output is going straight to those individuals.
I think most humans today massively underestimate just how absolutely shitty the life of a medieval peasant was.
You would have lived in a one room house without electricity, worked the fields from childhood (if you survived childhood), eaten simple foods without spices, watched your friends die from illness, then maybe get conscripted into a medieval war.
You don’t have to go to medieval times for that. The first half of the 20th century was like that for a lot of people in what is considered rich counties today.
In the cities many large families (or multiple families) shared a tenement and TB and polio ran rampage. Outside the cities many families lived inn1 or 2 room homes with dirt floors and no plumbing in many cases. This was common in Appalachia and parts of the south into the 1960s.
Millions fled many parts of Europe for these conditions in part because it was better than what was going on over there.
We are all seriously lucky to be alive today with what we have. And although these things are relative there’s no guarantee our societies continue to have such plentiful access to food, comfortable shelter, and basic medicines like antibiotics and vaccinations.
"It could be worse" is and always has been a garbage argument.
The problem is those oligarchs are using their outsized accumulation to lobby for and purchase a worsening world for their benefit. Sure, things got better for some people for a while. Now they're getting worse from what flows out of the discretionary spending of those oligarchs.
Claiming society hasn't massively benefited from productivity increases over the last century is certainly a take.... typical western raised privileged person claiming how terrible everything is.
It's definitely slowing the last couple of decades and in some aspects - reversing.
U.S life expectancy is one measurement confirming this.
Depression / anxiety among teens is higher.
And the last decade was pretty comfortable economically, it's going to get much much harder now.
I don't mean to say that there has been no benefit to the masses. I'm saying there benefits are clearly massively unequally distributed as the 0.1% get an ever increasing share of the wealth.
Is what you could claim if inequality wasn’t a detrimental to quality of life in and of it self, a fact which psychologists and sociologists have pretty well established at this point.
Also ignoring climate change, and how disproportionately it affects those less well off while overwhelmingly caused by the rich. Your quality of life may be better than in the 1950s, but this is going to be reverse really quickly over the next 50 years when we are hitting 2-3 degrees of warming, unless you are part of the 1% that can buy your self out of the crisis.
Sure, you can downplay the effects all you want, but this has been thoroughly studied, and there is a consensus within the scientific community that the negative effects of inequality are real. Disputing it at this point is kind of like disputing climate change.
If all of Bezos, Musk, Buffett, Ellison, and Gates’ wealth were instantly destroyed, inequality would fall quite a bit and yet my life would not be improved in any discernible way.
That is not how this works. Collectively (all else being equal) a lot of lives would indeed improve, or at the very least, the collective perception of the quality of life would improve significantly (in a statistical sense).
What you are saying is the equivalent of stating that today is cold, so climate change must be false.
Their possession of vast wealth is not a negative for me, nor would its destruction benefit me. There’s very few cases where we are competing against each other for goods and services.
If you’re asking whether I’d be better off if you instead seized it and gave me some, of course I would, but it’s important to understand that that improvement comes from being given money, not by the reduction of inequality.
Its been a while since I read the literature, but if I remember correctly, this effect you are describing is usually controlled for. If I remember correctly, it is the inequality it self, that decreases quality of life, and is independent of the increase in wealth among the poorer public.
That is, over a certain baseline, an increase in wealth does not yield significant improvement in quality of life (i.e. diminishing returns). Redistributing the wealth to increase inequality will improve the collective quality of life, not because the general public has more money, but because there is more equality.
Again it is up to you if you don’t believe this, just be aware that your believes are contrary to the scientific consensus.
I’m not sure if you’re inadvertently or intentionally trying to move the goalposts in our conversation.
There’s no doubt that money has a declining marginal utility. That’s as established an economic fact as they come.
There is still a leap from that fact to concluding that reducing inequality by vaporizing the wealth of five well-known billionaires would improve the economic lives of hundreds of millions of people. I believe it would not.
I do agree that if that were true, it would be strong evidence that inequality standing alone is causally negative (rather than merely a lack of redistribution being the actual negative and inequality being merely a correlated outcome, which is what I think is the case).
I’m sure this is not this simple, and I’m sorry if hinted that it was. Just how rich the richest 5 people in the USA are, is really emblematic of the wealth is distributed, you can’t just take away their wealth and leave it at that, you’ll have to shave off the wealth of the right-hand side of the wealth distribution curve such that the 5 richest people aren’t so filthy and unbelievably wealthy as they currently are. This is how things work in the real world, and what social scientists create their models after, and that is what I’ve been assuming you meant. Not a magic scenario in which the five richest people, and only the five richest people have their wealth erased.
Throughout this thread my goalpost has always been that inequality is in and off it self a detriment to the quality of life for most people. This effect has been measured, thoroughly studied, and is real, we shouldn’t be debating about that, because, if you don’t believe it is real, you’re believe runs counter to the scientific consensus and there is nothing I can say to convince you. However you seem to be in disbelief about how it works, so I’m gonna provide a plausible scenario. Note, I am not a social scientist, and surely there are more informed guesses out there, if you have the time, and are so inclined, you can probably find better sources on the web that explains this better.
In an unequal but wealthy society access to basic needs might be available to all. However access to other things which affects your quality of life is distributed. You might have access to education, but of lesser quality than the richest 10%, this gives you lesser access to better jobs, etc. Healthcare has a similar story, and so does recreation. You might have to settle for a badly moved lawn shared by dozens of people, while in another part of town the rich have a giant polo-field which is hardly ever used. In a more equal society, that polo-field may be repurposed to serve more people, access to health care and education is more equal, and the overall quality of life is improved. This is regardless of how much money is in the hands of the lower classes.
Note that this is just me—not a social scientist—guessing how this works, so take it with a pinch of salt. Other people have done quality research into this, and know it better than me. However, it may very well be that the mere fact that you have people that are this rich, really incentivizes the society around them to accommodate them, and their interest, at the cost of accommodating the rest of society.
In all those stories, it is the redistribution of something better to people originally without it that is the agent of change/improvement.
The analog where inequality alone is a problem is if you take the polo field from the wealthy and make it unusable by everyone. That doesn’t make anyone any better off.
People who talk about inequality are almost always actually seeking redistribution but have the sense to realize that arguing “I want what these other people have without working for it” garners much less sympathy than if they frame it as a global inequality.
That's by design. The whole point about making you fight between blue or red in the US and other fake dichotomies around the world, and have you overindex on some specific social/Identity issue is so that you don't realize that the divide is socioeconomic and democracy is mostly a sham because whoever gets in power doesn't have to serve the interests of its voters but those of its lobbyists, and that's exactly what happens.
But hey, that's radical talk,sentiment analysis suggests we should disable this kind of speech and keep our head down, lest we be denied more rights...
There isn't really any non-violence. The common solution to depriving people of their ill-gotten wealth is state coercion under threat of violence. I don't know if that would work in the case of the 0.1%, but we surely can't limit ourselves to non-violent solutions for the ultra wealthy when we have no trouble with violent solutions for the less wealthy.
It's time for the "without violence" to, once again, become of no importance compared to "ill gotten" (plus, with ever expanding definition of "ill"). That's what tends to happen, historically. We'll then get a decade or two of reconciliation and then will again start pretending that we're not murderous primate bastards we are, just like we did for the past 50 years (and even that not nearly universally).
Why should you play with a handicap? The "oligarch" forces you to work with violence. They've already violated the non-aggression principle.
No work? No money. No rent payment? Eviction (with violence). Stealing food? Arrest and imprisonment (with violence). It's violence all the way down. It always was. It's just a question of how it's organized and rhetorically justified.
How do you do it even with violence? How would you seize and “redistribute” Jeff Bezos’s (for example) wealth? It’s mostly in stocks that would start to lose value if you tried to cash them all out at once.
This is a non-issue; the stock will temporarily lose a bit of value through the increase of supply and that's it. Amazon as a company would still intrinsically be valued at hundreds of billions if not 1+ trillion, even if Bezos were to die tomorrow and his will would say that all of his shares should be sold on the market within a day. The fact that you might only end up redistributing $70 billion instead of the $80 billion he was worth when alive doesn't matter, it's still $70 billion being redistributed.
Laws that force Bezos to open up his platforms to competition would likely collapse the share price while not killing the actual value of what was built.
Tax is another.
The problem is getting into a position where you could pass those laws without violence. I'm not sure it is possible to do it democratically in such a corrupted political system. 3rd parties are essentially impossible and oligarchs have a lock on the other 2.
You disable his AWS account and badge and stop inviting him to meetings, likewise for any other hands that that stock falls into. It's not valuable if it doesn't give the holder enough power to make changes happen.
Think one step further. What happens if you do? Doesn't the USSR example teach you anything? You will have a different breed of oligarchs, that's all (yes, there were oligarchs in the USSR, just not in the way you think, money is not everything and oligarchy is not about money).
This is one of the most important questions we should be asking today. I'm not even joking as I think it's a critically important part of fixing society
As dumb as it sounds I genuinely think it's a concerted effort to change people's minds - specifically those people who want to become capital class or otherwise are on the way to the capital class.
If we can 1. Prevent new billionaires from being created and 2. then create structures to allow the capital class to feel like they are important to the process of reducing their own power and democratizing the economy, there might be a chance.
> This has been the promise over and over again, for centuries, and it has consistently not paid off. Where's the predicted society where automation allows us all to work for two hours a day, and spend the rest at leisure?
In the “Sad Irons” chapter of Caro’s LBJ biography, he talks about the pre-electrification lives of Texas farmers. In comparison with that, our whole day is leisure.
Similarly: As late as 1900, the poor in Europe were so severely malnourished that growth stunting was common. Look at Our World in Data’s charts of height over time. Or Robert Fogel’s “The Escape from Hunger and Premature Death.”
> This has been the promise over and over again, for centuries, and it has consistently not paid off.
You are working the same number of hours as before (40 ish) because companies are producing 10x as much goods in the same amount of time. If they produced only the same amount, ie 1x, you'd have your 2 hour work day (or more likely be out of a job). It is because companies are producing more stuff that you have a job at all currently. You are complaining about the very thing you benefit from now.
>You are complaining about the very thing you benefit from now.
It's dubious that anyone except the most wealthy benefits from this. Even though productivity has exploded, wages hasn't followed and the rewards of productivity has gone to a small few. I don't know how anyone can look at wealth inequality today and think most people should be "grateful". It's more likely to me that rest of America will start to look like San Francisco.
Although that's true, it's important to acknowledge that you've shifted the conversation from time, which was the original topic, to merely having things in a world where most people have little flexibility in the amount they work anyway. Even if I hadn't bought that phone, I wouldn't necessarily have any more time to myself.
There are many ways our lives are better. See for example infant mortality. To be born mere sixty or eighty years earlier would mean for me personally to die at three months of age. All my time is extra time if you look at it from this perspective.
I don't think anyone disputes that such metrics are better than before; the issue is staying complacent with what we have in a world where we are seeing yet another wave of potential productivity gains being captured by people who can afford to use it to gain more time. Saying "Things are better than they've ever been, why complain?" feels like the wrong approach.
"Hey, at least I'm not dead." as the answer to "Why haven't we seen meaningful increases in free time for first world workers over the past three decades?" is a real head-scratcher.
I mean that we, as a society, had chosen more goods and higher standard of living instead of free time.
It's not an exclusive choice either. At least in Europe, the amount of free time grows with each generation. 37.5 hours per week, 5 weeks vacation and many bank holidays is a significant change from how much people worked in the fifties.
Yes, we can do better. But both our wealth and our free time are visibly improving.
Who is staying complacent? We don't have increases in free time because work is not zero sum; technology enabled more productive work to be done (human computers versus, well, electronic computers) but we still have a lot more work to do. We haven't even reached type 1 on the Kardashev scale, meaning that we have yet more to do.
AI will similarly increase out productivity but the work will still continue, because humans are an inexhaustible species, we always want to do more and more.
I disagree. Having that phone means I do not have to go to the grocery store, etc. having the TV means I don’t drive to the theater. My very nice smoker means that not only do I not drive 20 miles to the nearest good BBQ, but I get time for myself to cook.
Many of these advances in consumer goods absolutely create more time for relaxation and enjoyment.
I already had those eight hours (after work, before sleeping) to myself, and as much as I appreciate the fact that modern conveniences make it easier to squeeze as much as I can out of that time, the amount is still palty compared to eight or nine hour work days four or five days a week. The issue isn't so much that I can come home and get things done, it's why the vast majority of people think it makes any sense to slave away for eight hours under the watch of someone else because... that way I can buy my own smoker?
I disagree, technological progress and productivity do not seem to be so tightly linked.
If we woke tomorrow and started making all goods to be long-lived, nothing single-use, fixed up the designed-in obsolescence, open-sourced everything, then we'd release people and resources for a great focus on innovation whilst simultaneously cutting production levels.
Because we spend a whole heap of our productivity on making crap, basically separating people from money as effectively as we can fit as little development as we can get away with. Our financial system (UK, I'd say The West is all the same too) is tailored to make rich people richer, everything else is a by-product.
Yes, people would work less (and produce less waste). No, I don't have all the answers on how that would work out. Greed would probably cause it to fail.
>You don’t have a smartphone, don’t use wireless networking and telecom, have no flat screen TV, don’t use the internet, and so on?
Bread and circuses? I mean sure, some things are cheaper, but other things are also much, much more expensive. And maybe it's because I'm older now, but I don't think "flat screen TVs" are a good benchmark for overall wealth (I don't even own a TV).
Yet, things like healthcare, housing, childcare and education have exploded in price despite the gains of "productivity". The former are necessities to live and it's dubious that to argue that I've "gained" from productivity if you have traded the ability for me to own a home with an iPhone. The balance isn't there - and I think you have a political undercurrent of people waking up to this. What good is a flat screen TV, if I can't own a home? Have I really benefitted from productivity gains if the equation is so out of whack? Simple math tells me that while a 50in has gone from $9,000 to $1,000, a "starter home" has gone from $200,000 to $800,000. Telling me I've benefitted in this situation is to take me for a fool.
Don't conflate lack of wage growth to the underlying reasons for those costs exploding. Why have those exploded?
Housing: NIMBYism and lack of ability to build, mainly by strict government zoning and people who petition their local governments to not build more lest it devalue their house.
Healthcare: insurance companies trying to get away with as much as they can, while hospitals try to charge as much as they can, effectively creating a price bidding war with the consumer in the middle.
Childcare: More people working, lower supply of childcare services but demand goes up, thus price goes up.
Education: Government effectively making student debt undischargeable in a bid to get more people to get college degrees but this backfired. Administrator costs for colleges ballooning.
So, even if wages had kept up with productivity, if you don't solve the underlying reasons as to why these costs exploded, you'll have the same issues as before.
Anything the government subsidizes (healthcare, mortgages, education) has exploded in cost because it’s built on a foundation of moral hazard. In essence the policies, which try and mix central economic planning with free markets, are lining the pockets of banks (guaranteeing mortgages), university endowments and admins (giving anyone with a pulse tons of money to learn), and healthcare providers (Medicare and Medicaid demand saturating resources by paying under market for the highest risk people).
I’m not saying socialized or free market approaches are better than one another. But the approach we have taken is the worst of both.
You can’t just insure the sickest demographics - you need a distribution. Either make it universal or let the free market compete for it.
You can’t just give anyone a ton of cash to learn what they want. Either make it free for all or let the free market lend to students based on expected return.
You can’t just guarantee every mortgage which keeps interest rates artificially low. Either build social housing or let the free market set interest rates.
I agree wholeheartedly. The mixture might work in other regulated domains like finance, but for the above, it only hinders true growth and development for the tax payer.
I know that comparing averages is not always correct, but. Median home price around 1975 was $100K (give of take), median family income: $14K. Today the median family income in MA is $75K. The median home price in MA is around $550K. You were saying prices went up and you can't afford a home anymore? Then you couldn't afford it in 1975. Should we go back a couple of centuries? And yet we have TVs, Internet, smartphones etc.
Indeed, commenters here seem to be looking at housing as a fixed good with the same supply without considering that maybe the fact that housing is still expensive is that we aren't building more housing, not necessarily that our wages stagnated.
This is a red herring. The reality is that the benefits from all this productivity are distributed to a few billionaires, rather than everyone.
Imagine how different the world would look if the richest person's net worth was a few million, and wealth was distributed much more evenly. You don't even need to look at productivity for this.
It wouldn't look substantially different. Wealth is not cash, you can't just redistribute it. And even if you could, say, take the top 100 billionaires' wealth (let's say they collectively have 1 trillion USD in assets) and redistributed it, the US tax base itself contributes something on the order of 2 trillion a year. So, great, for one year you increased people's incomes by 33%, increasing inflation as well, mind you. Now the next year everyone who's rich and invests in larger projects would leave to a country that doesn't have wealth redistribution measures, and the US would basically turn into Cuba. We gain a lot more from investment innovation through technology, empirically, than we lose through wealth inequality. The current system we have is the single greatest driver of human prosperity the world has ever seen.
I don't mean the US model of capitalism particularly, I just used its tax base calculation as an example (and either way, doesn't seem like you addressed the situation of what happens when you redistribute funds). I mean the modern system of free trade, regulated markets of supply and demand, comparative advantage, and so on, how most modern countries' economies function today. For example, India after opening up their markets in the 80s (having previously followed the communist Soviet model) has seen massive growth in terms of the wealth of their population.
Inflation occurs when the supply of money flowing in the economy grows. Bezos' wealth for example is tied up into Amazon, it's not liquid. But suddenly if you gave everyone and extra 10k a year from that money? They'll spend it, causing prices to increase. That's inflation. Not to mention converting Amazon stock to cash would cause the price to crater. The way to get around that would be to directly issue the stock to the government or to the people, as some countries do. However, again, people could simply sell the stock to use the money as cash, again causing inflation. Norway and Alaska have a decent model, a sovereign wealth fund that issues dividends to its populace, but again, it can cause inflation.
Oh, I don't disagree that the current system isn't bad, but, as you said, the Nordics have a much better take on it. Basically, aggressively taxing high incomes and having a strong social safety net seems to work very well.
On the other hand, Europe doesn't really have many companies on par with the US, likely because of the pro corporate policies in the US. Google, Amazon, Apple, Facebook, Microsoft, Coca-Cola, Nike, etc. Many companies that people currently work at are US made and it appears that the ability for people to start businesses is what enables our continued GDP growth such that we can even have a good economy. Compare to something like Italy or Japan whose economies are flat, as well as not having new entrepreneurial growth.
Now one might say that worker comfort matters over companies being made, but at some point, there have to actually be companies to work at in the first place.
We wouldn't have the invention of ChatGPT I would imagine. The pooling of resources to create such a thing probably wouldn't of occurred, or not as soon.
All you’re saying (by implication), besides not discussing numbers (which can show widening gap), is that you believe capital and state are necessary and exclusively capable of a productive and innovative society, that populations are otherwise inherently lazy or impossibly conflicted. I don’t think modern anthro research agrees with this. Catch up on Graeber & Wengrow
> you believe capital and state are necessary and exclusively capable of a productive and innovative society, that populations are otherwise inherently lazy or impossibly conflicted.
Where did the parent say anything like this at all? I believe you're attacking a strawman.
Another commentator calls out all the things we didn't have at all in the past, but our wealth in regard to pre-existing things also has gone up.
In the 50s there were 3 cars/10 Americans. Now it's 9. Homeownership went for 55% to 66%. College degrees 6% -> 38%. We used to spent 20% of income on food. Now it's around 8%. Poverty among 65+ went from 35% to 10%.
We need that many cars because our walkable cities were bulldozed to build highways through them. We need the college degree because jobs don't train you anymore and the few jobs you can get with little/no training were automated away or don't pay enough to live. The cheap food sucks and is killing us.
I'm 100% in on walkable cities, public transit, massive zoning reform etc. But were American cities more walkable in the 50s?
Yes, more jobs today require more knowledge. My grandpa worked in a factory full of boring, repetitive work where he also got to inhale bad fumes every day. I went to college for 6 or 7 years and my employers combined have probably spent less than 10k on training for me. I get to work at a sit/stand desk, get snacks provided, ergonomic equipment and do work that has much more variety than anything my grandpa did. Even if I ignore the astronomical income difference between me and my grandpa, I'd still not trade this for his job.
Was the food actually healthier in the US in the 50s? Did food not come from factory farms? Wonder Bread has been around since the 20s and in the 40s had to have vitamins added. Seems like we already were far away from the serene pastures we all like to imagine food came from. Looking outside the US, famines were incredibly common until quite recently.
We need that many cars because having own home and living in a suburb is an American dream, isn't it? How many people want to live in a high rise building with noisy neighbors? Yes, it is expensive, but living in a cave is pretty cheap, somehow nobody wants it.
I really hate how the wealthy benefit from my washer, dryer, dishwasher, Internet, air conditioning, access to a huge variety of food... When will the wealthy start passing the benefits of progress on to the rest of us?
We've got big problems in our economy and income inequality is certainly one of them, but it's asinine to pretend that most individuals in society have not benefitted from technological progress.
Different time scales. Except the internet these are all things that come in the last 100 years. Clearly average well being has increased in that time frame. Less clear if the last two decades have been advantageous for people in the US. I understand there are solid stats that the median person in the world and the bottom quartile, have improved.
My kids have a vastly more fragile lifestyle then I did right out of college.
It's weird that in the face of growing evidence[1][2], people will still argue that it's "asinine" that a lot of people got the short end of the stick. Imagine we both went fishing and I took 80% of the fish and gave you 20%, when you turned around and asked for 50% if I said "look you were hungry yesterday and you clearly benefitted from 20% of the fish, why are you complaining" I assume you wouldn't just say "ok you're right".
Even your list is out of touch; many of my friends in San Francisco don't have in-unit washer or dryers. Look I don't even think I'm even making a crazy observation; I'm just continuing the trend - as AI gets better and more pervasive it's only natural that wealth will concentrate without some force to redistribute it (either through wages or taxes).
Your fishing example assumes a zero sum economy, when one of the first things you learn in economics classes is that the economy is not zero sum, that comparative advantages enable positive sum outcomes.
A better example is, we go fishing, I catch fish, you chop wood, we build a fire with my wood and eat with your fish. We are both better off than we were before.
The metaphor is not the economy - it's about being told to shut up in the face on inequality. At the end of the day if I can't raise my concerns and negotiating, then I might as well be under a monarchy and we can erase all pretense about this being fair.
Well, we're talking about the economy, which is where you implied the inequality. My point is that you're making it seem to the reader that you're conflating the two things, making it seem like you're implying that the fishing is about the economy.
If you want to talk about shutting up in the face of inequality, pick a better example, or better yet, mention that you're not talking about the economy at all, even though that's the point of discussion here.
>mention that you're not talking about the economy at all, even though that's the point of discussion here.
Are you implying there is no income equality today? I don't understand your contention with my point. It's more just asking me to ignore actual data and be happy with the fact that I can buy a flat screen TV for $200.
It's seems natural that capital accumulates - and with AI this process is only going to get more concentrated; and looking backwards its clear we its only going to get worse.
Income inequality in what? The...economy, right? This is why I was confused, since you say your analogy is not about the economy, yet that's what we're talking about.
Income inequality in the economy is present, yes, but economists are not in agreement whether it's a good or bad thing, and whether redistribution of wealth would even solve it [0]:
> Despite the extensive existing literature on income inequality and economic growth, there remains considerable disagreement on the effect of inequality on economic growth. Existing literatures find either a positive or a negative relationship. In this paper, we attempt to theoretically examine that relationship with a stochastic optimal growth model. We make the disagreement clear within a single model. We conclude (i) that both are possible – that is, higher inequality can retard growth in the early stage of economic development, and can encourage growth in a near steady state, (ii) that income redistribution by high income tax does not always reduce income inequality. Income inequality can be reduced by higher income tax in a near steady state, but it cannot be reduced in the early stage of economic development, and (iii) that two government polices – rapid economic growth and low income inequality – can be achieved by low income tax in the early stage of economic development, but both cannot be achieved simultaneously in a near steady state.
Now if you would like to submit literature on this topic, please do, as simply talking about what seems "natural" or "clear" does not really mean anything.
NIMBYism and lack of housing development, whether by government or by corporations. In countries like Japan where housing is not an investment but a depreciating asset, people can buy homes. Because, well, they build enough.
I mean in the major cities where had been still growing in the post war boom. Even looking back then, housing was still a depreciating asset, not an investment.
This promise had to be fulfilled by those whose salary depends on not doing it (us). Do you really believe that automation is at its peak availability now? I think we diverge from it more and more. Even as a programmer you meet a bunch of barriers to automate yourself or your home, office, etc. Every little thing is complex af. The society that automates everything is coming, I hope, bypassing the heap of nonsense we’ve built.
> > that means that many companies can potentially produce 10 times as many products/services and make more things that will enrich peoples' lives.
> This has been the promise over and over again, for centuries, and it has consistently not paid off. Where's the predicted society where automation allows us all to work for two hours a day, and spend the rest at leisure?
Is the promise you're referring to that work will be so valuable that people need only work less than a quarter as much to live a material lifestyle equivalent to CE 1823 or 1923, or that there will be so much work to be done that there's no unemployment to speak of in 2023? Both of those seem to be true...
Why? An AI when told "follow local labor laws" is actually going to do it perfectly. Whereas those boards of executives are very happy not doing it.
A workers co-op owned company headed by an AI decisioning board would be able to maintain constant, real time feedback and coordination with all workers, and would be faster and more maneuverable then human headed companies.
>Where's the predicted society where automation allows us all to work for two hours a day, and spend the rest at leisure?
That’s not the fault of automation. As a society we’ve chosen to increase our population and level of consumption instead and automation is simply the engine for it.
Not possible because you don't set the prices or structure for obtaining goods and shelter
It's not like there's unclaimed habitable territory that anyone can just go be subsistence farmers on - someone has laid claim to that land and it's not you
So, no this isn't an option either as you're forced to interact with the rest of the world that demands your input
A few hundred years ago, you would've lived in a shed with 6 people on 10sqm. I'm sure you can get that kind of accommodation today for very little money.
If you want 2023-level housing, you'll need to put in 2023-level work, unfortunately.
It's true for them, too. A rich guy's life in 1800 sucks compared to the average person's life in 2023. There's a reason why there's no rush to emulate the Amish, and they're not even that extreme.
No, it's some intentional decision of a suburban family in Kansas to not go be Amish. That's not how societies work.
And no, life is worse for millions of people around the world than it was in 1800 if for not other reason
This idea that things MUST be better just isn't supported with data. All the "data" about how great the world is is bad statistics - it's looking at averages only, not the distribution.
You can't point to the richest areas and claim "look see how great things are?"
Find the most destitute among us and see how they fare
> And no, life is worse for millions of people around the world than it was in 1800 if for not other reason
Yeah, but not for the same people. Life in 1800 in NYC was worse than life in NYC in 2023 for the average inhabitant. Life in some places on earth today are worse than life in NYC in 1800 was, but that's not the question.
> Find the most destitute among us and see how they fare
Better. They're faring better. The data is in, and they do.
How do you square that rationalization with the fact that you could buy a house on a high school diploma and a factory job back then? :p (With a pension! Everyone had those back then. What even is a pension? I don't know. It's something like "the company keeps paying you when you stop working", I think, but it sounds dope.)
I think if you compare then vs now in absolute terms, you'll find that the house wouldn't be considered adequate today, the insulation was bad, the plumbing questionable and electricity wasn't there (depending on when you compare to, but it needs to be sufficiently far away, few people said in the 80ies that nobody would work by 2020).
Quality today is generally much better and "average" isn't the same. I read a piece one some woman who lived around 200 years ago and she traveled to a city ~100km away, which was a noteworthy biographical event back then. That's a distance some people do daily on their way to work these days. Travel to a different continent? You'd be exceptional if you did so once in your life, today that's available to most people in the West to do once a year (granted, it won't be the luxury version, it'll be like my trip to NYC 25 years ago where we stayed in a hotel that was being renovated, the elevator was out once and we had to climb 12 floors but it was super affordable).
Is this actually true though? Suppose you want to own a house and a car, not to mention be able to send your kids to university. That was affordable 50 years ago, and the only one of those things which has gotten better is the car.
Fifty years ago was still in the post World War 2 economic boom. If you want that again, all you need is another devastating world war that kills tens of millions and wrecks every other economy except that of the United States.
That isn’t just motivated by greed. In a competitive industry, if you take your foot off the gas, a hungrier competitor who is willing to go home at 5pm or 6pm will eat your lunch.
It’s partly a product of capitalism within a nation, but also a product of the basic struggle for wealth and power at the international level. This is a common discussion in my chosen industry; we have well paying jobs and good working conditions, but only because we are (significantly) ahead. Our lead, and by extension the good life, could completely vanish in five to ten years if we stop pushing forward.
> This has been the promise over and over again, for centuries, and it has consistently not paid off. Where's the predicted society where automation allows us all to work for two hours a day, and spend the rest at leisure?
The end result of creative destruction is not so we can all work less, it's so things that we value become cheaper, allowing us to reallocate resources to things that are equally or more valuable. It gives rise to new companies and industries that either a) could not work without the new tech, or b) were prohibitively expensive.
The classic example is the fridge. Before it existed there was an entire industry that revolved around transporting blocks of ice. Now imagine all the industries, technological advancements, scientific advancements that would not exist if we didn't have the ability to make a box really really cold, relatively cheaply.
Creative destruction leads to economic growth (increasing the pie), not a society that doesn't have to work 40hours a week.
> Where's the predicted society where automation allows us all to work for two hours a day, and spend the rest at leisure?
Others have already commented on the fact that quality of life has generally increased.
I think it's also worth realizing that over the course of a lifetime people today spend a much smaller fraction of their waking hours engaged in work than before.
100 years ago a typical man in a developed country might have started work aged 14 and then stopped working a few years before death if they were lucky to not die before.
Nowadays even someone "uneducated" would start working at 18, while others might start aged 22 or older. And a common expectation is to have a retirement of 15+ years.
So averaging over a lifetime we do work a lot less as a fraction of our lives than in earlier times.
Edit: numbers were plucked from thin air based on my experiences of my own country, but i guess the general point applies to most developed countries
I have a hard time believing that more jobs would be created. Like what a prompt engineer? As far as LLMs go, only companies that can afford the compute seem to be building one from scratch. So I don't think any new ML engineer jobs are going to get created
> This has been the promise over and over again, for centuries, and it has consistently not paid off. Where's the predicted society where automation allows us all to work for two hours a day
That's the opposite of what GP predicted: that people would be more productive and produce more, not work less.
Programmers are way more productive than the were sixty years ago. We don't have fewer programmers, or part-time programmers, but we do have vastly more and better software.
> Companies have shown time and time again that they're willing to make this trade-off.
Maybe they wouldn't, but then the insurers come. Not all of the 1% of errors from an AI will be disastrous - if it happens to be "jaw-droppingly destructive" rarely enough for the insurance to make sense economically, that AI will be used.
Productivity metrics have gone up dramatically. Surplus from automation goes to owners (or the state). Worker gains are a market - in other words, capital and state organize and aim to minimize those gains as a negotiated cost
>>This has been the promise over and over again, for centuries, and it has consistently not paid off. Where's the predicted society where automation allows us all to work for two hours a day, and spend the rest at leisure?
<<
I personally would hate to spend all my time on leisure activities. I would still be working as hard but on my passion projects.
No offense but who wants to spend most of their time on leisure activities. That gets old fast. It is a lot more fun being productive. Maybe I'm just weird.
A person on minimum wage in the USA today can enjoy a higher quality of life than kings of a few hundred years ago. My point being that automation has brought huge benefits to society, even if we are blind to them.
>I would still be working as hard but on my passion projects.
That's called leisure, being able to direct your actions without worry about them paying the bills, leisure.
Of course you could choose to vegetate in front of a screen, but you're also free to walk the hills, create art, create machines, write software or poetry, or whatever.
In this context, "leisure" is used to mean the stuff you do outside of work and chores essentially. If you want to work on a side project, that would fall under leisure time.
> Many people can easily create a similar quality of life to 70 years ago while working 2 hours a day.
Please explain. I think you're underestimating how much things have changed, and are making a lot of assumptions about what you mean by "quality of life .. 70 years ago" and "working 2 hours a day" that would not be obvious (or available) to other people.
Who even wants to work just 2 hours per day. Sounds extremely boring. Work is a great way to exercise your mind and body while simultaneously earning funds to purchase luxuries.
People who claim that modern industrial tech and advancements have not benefited society is arguing that they are not being disproportionately benefited.
Industrial automation did create the 2hr weeks - only that it's the people who paid capital and and invested in their creation that got those 2hr weeks.
But everybody else got the benefit as the general access and availability of many more goods and services than otherwise would've been possible.
But having a lot of easy to access food certainly does. Or what about clean water, or electricity? Or cheap transport? When has there been in the past, before the advent of industrial automation and technology, that people could just travel on a whim somewhere more than a day's walk away?
Just because some symbol of luxury like the iphone is what you think of as "more stuff", doesn't mean it is. "more stuff" is _everything_, and while it does include the iphone, it also includes the cheap phone that makes it possible to communicate almost for free with almost anyone close or far.
The tickle down has been happening for the past 70 years, and the regular people have been benefiting so much that it looks normal now. I would use the analogy of boiling a frog, but somehow this doesn't quite suit.
>The tickle down has been happening for the past 70 years, and the regular people have been benefiting so much that it looks normal now.
This is just not true based on the data. The rich eat well - but food insecurity is still RAMPANT because of greed.
Food is less healthy now than ever and the majority of the population is malnourished - that is to say eating the wrong thing - despite us having enough capacity to produce quality food for everyone.
Food deserts ensure that the poorest people get the worst food.
Because they don't have as much money as other areas so people follow the money with where they provide services
>tend to lack education, including knowledge about healthy foods
This is also true and again structural - see above. Poor areas don't get school funding because school funding is based on county property taxes and thus, do more poorly than rich areas
It literally all boils down to structural inequality
Because they quality is so bad and the prices are so cheap.
Having lived in these areas for most of my life I can tell you it's often only specific low quality chains (Church's, Grannys, Jack in the Box etc...) or these "chicken wing/chinese food" shops that basically just fry up the worst meat and slather it in sugar sauce.
I recall in high school, peers of mine would simply eat a bag of Doritos for lunch - as even the classes like Home-economics were largely just holding cells for teenagers until graduation.
I'm not denying any of these improvements but there is also evidence that walking with this constant distraction and being bombarded by social media / news is bad for mental health and our ability to focus.
Because what would've been my self-sufficient tribe that needed nothing more than food, socialization, and shelter has been obliterated by various, human-made forces, and I now have to try and fill in the void by spending money.
Partly the social void via digital communication, and partly ancillary emotions generated by having something nice that makes my sisyphean pursuit just a little bit easier.
If I was able to live a life where I could see my friends and family, and be a part of a community, without any threat of that way of life being destroyed, I would not be working a job in a first world country.
Nor would I be stuffing my metaphorical and physical face with: entertainment, food, various media like video games, etc. Good company is enough to stay entertained for hours -- and it's free; but past a certain age becomes annoyingly more difficult to find as people get loaded on responsibilities, and time-commitments, and other things they believe are prudent for their "success."
I'm an extreme extrovert. My biggest gripe with capitalism is that it's alienated and killed the souls of all the people around me -- and now I have to spend copious amounts of money just to try and fill that void.
How about moving to Amish county? You always have a choice. Just don't expect to find there a social utopia where "everybody is free and everybody has at least 6 slaves", people are the same everywhere, with iPhones or not.
Yeah it’s like saying that if only we all had 800 hammers we’d all live like kings. Technology does not automatically make life better, only different. Better is a value judgement.
Why is the premise that a "better life" is one where we work fewer hours per week? Surely there are other dimensions on which to measure quality of life. Or maybe you'd prefer to live in Medeival Times? After all, you'd work fewer hours per week! Sure you might die at the age of 35, have your leg gruesomely amputated due to sepsis, or be burned at the stake for suggesting the earth spins around the Sun. But think of all the free time!
> Serfs in medieval Europe had very little free time. They were required to work long hours, usually from sunrise to sunset, and often had to work on Sundays and other holy days as well. Their work consisted of farming tasks such as plowing, planting, harvesting, and tending to livestock. In addition to their agricultural work, serfs were also required to perform labor for their lords, such as building and maintaining structures, repairing roads, and providing military service.
> Plowing and harvesting were backbreaking toil, but the peasant enjoyed anywhere from eight weeks to half the year off. The Church, mindful of how to keep a population from rebelling, enforced frequent mandatory holidays ... In fact, economist Juliet Shor found that during periods of particularly high wages, such as 14th-century England, peasants might put in no more than 150 days a year.
Oh, interesting. Isn't it only off from farming? I thought that's where making roads and dying in wars came in. But it's also true they had to have at least some free time to mate.
People are ditching their phones which to me proves their value isn't universal and probably isn't that great of a benefit to anyone other than business.
Your comment is amazing in its naivete. The first sentence in the post you are replying to already includes awareness of everything you said and more, while nothing in your comment suggests you understood the post at all. Priya doesn't become 10 times more productive, someone else uses the tool to do her job, which no longer exists.
Priya has a university degree in biotechnology. If that doesn't qualify her for something more productive than GPT-level work, there's something fundamentally wrong with the educational system.
She's in her 20s, educated, and lives in a country that, for all its problems, is on a strong growth trend. She's not a 60yo UAW worker in Detroit.
And yes there is something fundamentally wrong with the educational system and has been for decades. Companies doing ground breaking work have their pet colleges for recruiting and outsourcing, the rest just create outdated degrees for mega companies that used to exist. The students aren't great and the education is poor in most places.
> Priya has a university degree in biotechnology. If that doesn't qualify her for something more productive than GPT-level work
Don’t bio and related fields have an over supply? I was under the impression there weren’t enough jobs for people educated in these fields, especially not for “more productive than GPT-level work”.
That cycle has gone on since the start of the Industrial Revolution. Jobs are destroyed, people complain and protest, new jobs are created and the total economic pie and the absolute size of the average person’s slice increases.
A valid question is are there inventions for which this would not be true? I think yes for general AI, but also yes for people who are unable to migrate between a job lost and any of the new jobs created due to lack of education or willingness to reinvent themselves or relocate to where the new jobs are. Innovation can definitely create winners and losers. That’s bad for the losers, but not necessarily for society as a whole. Unless so many losers are created that they rise up and overthrow the system. That’s a real long tail risk if the pace of change sufficiently outpaces our ability to adapt to it.
You're right, but the phrase "people complain" elides a lot and shows a callous lack of empathy. People complain because they lose their jobs, their homes, their standard of living, their future prospects, their ability to feed their families, their relationships, their social status, their healthcare benefits and therefore their healthcare, their mental health, and in some cases their lives (suicide is not unusual for people who lose all of the above). For every Priya who gets a new job as an AI wrangler, there will be many who do not.
How that is handled really comes down to how your society has agreed to establish a social safety net.
In Northern Europe it’s handled quite well. In the U.S. it’s handled with a “callous lack of empathy” as you phrased it.
My point is disruption is the engine of progress, but it also causes temporary pain (that might not be temporary on the scale of human lifetimes.) It’s the wrong reaction to want to stop or slow progress. You can actually prove that through the lens of game theory and the fact that we have multiple human societies. The right thing to do is ensure your society doesn’t leave the losers of that process behind.
Sure, but many of the "progress is inevitable" people are also often the "get your stinking government hands off my hard-earned money" people. Increasing taxation of the beneficiaries of AI technology to provide a safety net for the losers is one way of dealing with it, but I'm not sure it's politically achievable in much of the world in a way that will instill confidence in the people who face the loss of their livelihoods.
"progress is inevitable": It's not actually. Progress is only made if people take the risk and effort to advance progress. That does require rewarding them appropriately for the risk taken. I'm not saying we get that balance exactly right currently, but it is necessary.
In general just taxing the winners (wealthy) period is well tolerated politcally, but it also requires a goverment that's somewhat fiscally responsible and not spending $800B a year on their military instead of social programs. The US hasn't had a fiscally responsible government since Clinton, and the pigeons are currently coming home to roost in the form of inflation and loss of confidence in the US dollar as the reserve currency.
Disruptions in the past have almost always been good for society overall, but there have also always been significant localized negative effects. For example, a farrier may have been thrown out of work and had to switch to unskilled labor, but their sons and daughters were better off.
The issue is that as change comes faster and faster, a higher proportion of people fall into the "disrupted" category.
Then you get a revolution and the whole system is torn down and rebuilt in a different form. That's highly undesirable, and as I mentioned, is a real tail risk to consider.
You are being pedantic. You also came by with a three word troll comment. Why don't you make your argument properly and then I'll spend the effort to address it.
It's important to consider the goals and motivations behind the development of AGI. Who is in control of this technology and how will it be used? The current power structure in our society is not interested in creating a better future for everyone. There is a growing concern that the development of AGI could be driven by the interests of a small group of people with a lot of power and money, rather than being used to create a better future for all people.
In this context, I think it's important to ask "progress towards what?" and to define what we mean by "better". We need to ensure that the development of AGI is done with a goal of benefiting everyone, not just the wealthy and powerful. This requires a shift in our political and economic systems, so that power is more evenly distributed and the needs of all people are taken into account.
I'm not saying that AGI is inherently bad, but we need to be cautious and intentional about its development and use. It's possible that AGI could be used to further entrench the power and control of the wealthy elite, rather than to create a better future for all people. To avoid this, we need to work towards creating a more democratic society where the benefits of technological progress are shared by all.
Ok, I understand your point now, and I agree with it for the most part. AGI really is a singularity. We can't see past it, and nobody knows what a society with AGI would look like, or even if there is room for humans in it. I think not. AGI will likely be our last invention as a species and the next step in natural evolution of life will be intelligent design (initiated by us!) Oh the irony.
So you're right that running full speed towards AGI is incredibly dangerous, and while it might still mean progress for life, it might not be progress for humanity. AGI may be one of the few technologies that are not progress. I'd argue nuclear fission so far has not been progress either, but that story has not yet fully played out. You could also think of other hypothetical and current technologies where the risks far outweigh the rewards. Imagine we find a way to unlock an energy so vast that a small group could unlock it and unleash it and super-heat the entire atmosphere of the planet, killing nearly all life. There's no law of physics that says that's impossible - and once discovered, there's no way to defend against some suicidal nutjobs doing exactly that. That's one of the solutions to the Fermi Paradox.
But AGI also may be our destiny - there may be no way to avoid it. Even if we could agree in the US to stop advancing AI, other countries will not agree, and so it continues anyway and the US just loses control over it. You can replace the US above with any country with the same game theoretic outcome. So game theory involving competing groups may possibly be an unstable system that ends in self destruction. That's another solution to the Fermi Paradox.
Then there's the detail that current LLMs like ChatGPT are not AGI, and probably don't lead there. They're a fancy parlour trick, but not really intelligence. So progress on LLMs may or may not bring us closer to AGI, nobody really knows. Stopping work on it now would halt progress, but only for those groups foolish enough to do so.
I don't yet see a path to being cautious and intentional about its development and use of AI. The genie is out of the bag, and can't be put back in. The same way nuclear fission can't be undone - although that's a bad analogy since it's much easier to control. Maybe we figure out a way to do that in future, but AI development is just the development and spread of information, and that's impossible to control.
What I think we can do, as you mentioned, is modify our societal and economic systems to be more fair and to not leave so many people behind who's skills have been obsoleted.
Also, I don't think you would need a human-like level of consciousness for a general problem solving device i.e. general intelligence. We could end up with a Deus Ex Machina situation where the general problem solving device appears to be human. Even exhibiting heart string pulling capabilities, not to mention cock string pulling capabilities, while still having the end goal being something absurd like going to a specific crosswalk at a Manhattan street and stand like a useless toaster.
That isn't the singularity, but it sure as hell is a general problem solving device i.e. AGI.
I think it's generally useful AI, but not AGI as people discuss the term. AGI would need to be sentient, self-aware. It would need to be alive and intelligent by any definitions of the term. ChatGPT is generally useful, but still very far from alive.
Anything short of that could mean large disruptions and societal changes, sure, but not a threat to humanity. Just technological progress as we know and love.
Don't most companies have a giant backlog of bugs and todo items? if you get a productivity books with AI you can fix all those bugs the users reported and implement the feature your users want, and implement that hard feature you always wanted to add but you did not had the time.
I mean that if an AI can make me more productive then I can tackle those TODOs , I agree you can't just hire a new dev for those tasks because he will need training in our code base,t hat will cause me to waste more time training , explaining , debating stuff. Anm AI could help with boring crap like I could ask it to review my code for potential bugs, maybe write some tests, in future it could refactor some bad code to be more clear , like better variable names, split it in smaller functions, replace deprecated syntax and function with latest stuff.
I think only a company with serious money issue would fire a good developer that you trained for years in your code base instead of letting him to focus on the TODOs/bugs and get things fixed and new features at a faster speed.
And get hired at a place where software development now being cheaper per unit of functionality makes it economically tenable for that firm to have SWEs.
> 2) Chaudry ignores that you need a human in the loop to check an AI's work. You don't know that an AI's answer is always right. Even if it's perfect in 99% of cases, the answer could be jaw-droppingly destructive in that 1% of cases and make errors that even the dumbest human wouldn't make. Being grossly wrong even a small percentage of the time is far worse than a human making minor errors sometimes, and being slow all of the time.
I very much doubt this will be the case and if it were, it's unlikely to be effective. We know people that have to check something that's right 99% of the time but wrong 1% zone out and overlook issues. It's a big part of why self-driving cars can't be a 99% affair and why people die when self-driving cars make bad decisions even though a driver is behind the wheel.
I think where profit can be extracted, companies will rely on good ol' lock-in or hope the cost of changing is too high to warrant a mass exodus from their platform. Everyone has a super computer in their pocket, but instead of improving typing we started adding "Sent from iPhone" as a way to excuse us from having to proofread anything. I can't count how many times I've gotten mass emails with template variables that weren't interpolated. Or emails that reference discussions that never happened. Ostensibly, a human was there to review all of this, but shirked that responsibility because ultimately they can let it waste someone else's time. I see AI turbo-charging that.
I think we're being disingenuous with all of these automated tools and thinking an attentive, caring human will check all that work. It'll be more profitable, whether in terms of a company's capital or an individual's time, to clean our hands and go "whelp, that's AI for ya" when things go wrong.
I appreciate the perspective shared in the article, but I can't help but find it somewhat egocentric. Firstly, it seems to overlook the fact that Priya was already being exploited in a low-paying job. The article describes the long hours and overwork she endures, but it fails to challenge the status quo of her employment situation. This lack of critical analysis may be indicative of a narrow focus on the negative effects of GPT-4.
Secondly, it appears that the author is using Priya's story as a way to gain self-importance in his blog, painting her as a victim of ChatGPT's progress. While it's essential to address the potential job displacement caused by AI advancements, using an individual's plight as a narrative tool seems rather opportunistic. A more balanced discussion of the broader implications of AI on society and the workforce would have been more informative and less self-centered.
I would guess that a higher proportion of HNers have had a chance to work with GPT-4 than the general population has. Most people are still basing their takes about AI either on something like GPT-3, or just what they're hearing in the general media.
The point of the article I that there are a lot more people in jobs like Priya's who won't be able to quickly leverage AI for their own benefit than there are who will. We throw the word "disruptive" around a lot here. But that's exactly what these new AI tools will do to many people's lives. Their lives will be disrupted, and they have little cushion to fall back on.
I believe technical progress is inevitable, but a lot of people suffer on the path forward.
Came here to write this. To expand #2 in a potentially obvious way, the HIL can't be any random person. In most cases, the subtle, destructive errors you're trying to avoid are only going to be caught by a SME with significant experience working without the benefit of three automated assistant.
Much in line with #3, I see GPT as a (IMHO, welcome) return to the days of a secretarial pool. You couldn't rely on a pool secretary to be conduct your business without oversight (because they had many Jr. Executives utilizing their services and weren't deeply engaged in your day-to-day like a dedicated Sr Executive Assistant might be), but they were experts in typing, drafting, and professional correspondence generally. GPT promises more, as it can express some level of subject matter expertise in almost every topic, but I believe that, for the foreseeable future, it will be best utilizable as a productivity enhancing assistant rather than as a full replacement for those with the expertise needed to check its results.
Edit: On the flip side, companies that still have secretarial pools (though I'm only aware of such pools still existing in government agencies, which won't be replaced due to need for secrecy) will probably end up firing a lot of secretaries.
> 1) Chaudry's article is amazing in its lack of creative thinking. If people like Priya can be ~10 times more productive wielding some AI tools, that means that many companies can potentially produce 10 times as many products/services and make more things that will enrich peoples' lives. Though some people in some companies might be laid off, it doesn't necessarily mean that more people will be laid off than new jobs are created.
"Trickle down economics" don't work. Industrialization waves wrecked the lives of many many millions of people over the centuries, while the people owning the factories eventually got richer than aristocracy as they kept the price of the sold goods barely cheap enough to be a bit cheaper than manual production and pocketed the immense difference in production cost.
> 2) Chaudry ignores that you need a human in the loop to check an AI's work. You don't know that an AI's answer is always right. Even if it's perfect in 99% of cases, the answer could be jaw-droppingly destructive in that 1% of cases and make errors that even the dumbest human wouldn't make.
Replace "an AI's work" by "a C-level executive". They can run a company fine in 99% of cases and in 1% of cases run it completely aground with extremely dumb short-sighted decisions (like we're seeing with Twitter, or with Boeing, or Credit Suisse), but no one cares about that and the execs still get their golden parachute. It will be just the same with AI - eventual failure will be priced in.
> Did accounting software make the world worse and destroy jobs even though it made 1 accountant ridiculously more productive than they were in the past?
The switch towards computerization wrecked the Western middle classes. It used to be the case that white collar jobs could feed a whole family comfortably on one income, and automation made it so bad that the majority of our populations has to struggle to make ends meet now, and completely forget about having children because we can't afford large enough homes.
> Trickle down economics" don't work. Industrialization waves wrecked the lives of many many millions of people over the centuries, while the people owning the factories eventually got richer than aristocracy as they kept the price of the sold goods barely cheap enough to be a bit cheaper than manual production and pocketed the immense difference in production cost.
(1) trickle-down economics-style policies aren’t the only way to harness the (presumed) increased productivity of LLMs like chatgpt.
(2) I don’t see how you can argue that standards of living have decreased since the start of the industrial revolution and subsequent technological developments.
Certainly, the question of how to distribute the benefits of wide-spread LLM use is very important, since it could be done well or could be done terribly. But there’s no reason to just assume terrible is the only option.
> (1) trickle-down economics-style policies aren’t the only way to harness the (presumed) increased productivity of LLMs like chatgpt.
There is no reason to believe that the rich classes will act differently than at any time before in human history. To the contrary, union busting laws have eroded the standing that the worker class had even a few decades ago.
> (2) I don’t see how you can argue that standards of living have decreased since the start of the industrial revolution and subsequent technological developments.
Yes, on a societal whole standards of living have risen, but a) millions of people have suffered regardless (e.g. it has been shown that those graduating during the recent economic crises face significant income losses over their lifetimes) and b) other metrics (ownership of assets like houses, financial savings) have gone dow hill at the same time.
As for your point 2), we already have humans in the loop of other humans and this commonly leads to the "why do companies have so many people in them" trope we see posted on HN commonly. I think in that sense you may be underestimating how incredibly stupid people can be too. This said, AI doesn't remove all humans from the loop, but may significantly reduce how many are in said loop.
As someone who has worked at companies buying the databases that come from manually reading papers, the quality of them is hugely variable due to this. Lots of manual errors, missing context, etc.
Plenty of drug activity databases don’t distinguish between assays in solution, cell-based, and in vivo. When these produce hugely different values for inhibition due to metabolism and transport in biological environments.
GPT4 opens the possibilities for the true experts to focus on prompt engineering to extract these details, developing mechanisms to test performance, think deeply on how the data is stored and organized, etc.
This is such a toxic response. You're commenting on someone's blog about how they are sad. Your response is to argue that they're wrong which means that their sadness is invalid.
This. Empathy. People acting like they sound smart when they talk like a USC sophomore who equates logic with truth. As if the human condition were an actuary table. As if triage was a guiding principle of human culture. This kind of thinking slips easily into fascism. Ayn Rand writ large.
Such a lack of nuance. We can pragmatically recognize that pandora's box has been opened and also, at the same time, have an ounce of empathy. We can even like where things are going, understand the negative impact on some, AND still have empathy.
What I see here is emotional immaturity and the arrogance of someone who never learned the value of maturity. Lazy thinking. Self-serving modes of thought that allow you to feel ok with selfishness. Unchecked capitalist ideology. The psychology of greed.
Yeah it will create jobs. And maybe make certain companies more productive.
As many are quick to point history has shown new jobs appear.
But it often take years or decades and causes a lot of individual stress and social unrest.
Hopefully it will be smooth for many people. But I don't think it will take long before chatgpt allows a team of 2 what now a team of 5 developers does.
What job will appear that a machine can't do better. Plumber comes to mind.
It isn't inconceivable however that Boston robotics couldn't hack that if they could connect one of their robots to a general problem solver that takes visual input.
But will you be able to afford this fancy artisanal therapy, yoga, massage coaching? There will be a general intelligence providing this via dirt cheap robots eventually.
> 2) Chaudry ignores that you need a human in the loop to check an AI's work.
Also ignores companies not wanting to pay employees. These AI verifiers will be low paid people, akin to the off-shored social media content checkers who have to sift through digital garbage.
> If people like Priya can be ~10 times more productive wielding some AI tools, that means that many companies can potentially produce 10 times as many products/services and make more things that will enrich peoples' lives.
It’s baffling to imagine that this would be the outcome of widespread use of AI. Ultimately this may be a philosophical question. To what degree do companies enrich the lives of people, vs. just sell then trash they don’t need? Particularly when it comes to the sorts of things that AI can produce: advertising copy, content, which will surely mean “engagement.” Ie, addictive trash.
Yeah but the new graduates are not equipped to enhance their work with AI (independently). The new graduates have already graduated through a curriculum based on self analysis and thought. AI will test their skills and make them obsolete. They are most at risk of structural unemployment.
The advent of the Internet did the same for those who graduated right before 2000. These graduates did not have skills needed to work with the Internet. And often found themselves going back to school to learn a new trade.
So, what are the chances that it is different, this time? If AIs are getting better and better, they might replace more and more jobs. What kind of new jobs are we imagining that cannot be replaced by a "near-intelligent" AI?
If that comes to pass, the only issue for the owning class I see is that they might not have customers in sufficient numbers, that are able to pay.
> that means that many companies can potentially produce 10 times as many products/services and make more things that will enrich peoples' lives.
There are some real problems here. For example can the economy even support 10X production?
Ag -> Industrial -> Information transitions were all supported by a mix of massive expansion in population, mass migration of populations, and globalization of economies
information -> automation transition does not seem to have these 3 things in the same way. Globalism is slowing or reversing into protectionism. Migration is still high but seemingly for different reasons (geopolitical) as people displaced for war, crime, or climate and critical for this discussion population growth as SLOWED way down, and it expected to reserve about 2040.
This means people looking at the historical models for how these tech disruptions played in are very flawed in their "everything will be just fine" handwavium
My prediction is we will see a MASSIVE increase in weath gaps, and extreme decrease in standard of living in most of the industrial world (we are already seeing this in a limited way) leading to more and more political instability
>that many companies can potentially produce 10 times as many products/services and make more things that will enrich peoples' lives.
See, that worked through the 20th Century because we, in the West, had effectively unlimited materials and unlimited energy - we just had people dig it out of the ground, easy.
But now we realise that fossil fuels wouldn't last forever, both because of environmental impact and it just plain running out.
Any plan for the future that requires us to produce more in order to get out of a crisis is 100 years too late.
We need to distribute the benefit of the efficiencies, not think we can produce 10 times as much junk because we made things more efficient.
But Capitalists thrive when we create more waste, strip more non-renewables, make more pollution.
Re 2) built in sanity checks aren't too hard; yes we'll keep humans in the loop for high-cost and life critical systems for a few more years.
> companies can potentially produce 10 times as many products/services
How exactly is that a good thing? We already consume too much, now we will have 10x as much to consume? Unlikely that demand for "the things" goes up 10x, which means the value will drop.
Also, it matters what you consume. I e a lot of work is only necessary to support other workers or ‚bs work‘ like selling ppl things they don’t really need.
I'm rapidly losing faith in "a company can provide good products/services". Maybe it's just because I hyperfocus on the software sector, where this seems especially true, but it seems like worse products (those that prey on and value extract from the user) make more money.
Companies seem incentivized to produce worse products, while preying on our worst impulses.
Convenience you become a slave to, not owning anything, streaming everything.
Why make this game good when we can simply make it addictive? (Shout out to Diablo Immoral.)
Why make it healthy when people just want it to be tasty?
Why not remove these features and charge you to get them back?
Why not spy on and datamine our users? They won't care enough to stop us.
Why not plan obsolescence in our products? Every competitor will be forced to follow suit or make less money and be eliminated.
These measures truly make more money, and companies are actively incentivized to pursue them.
It really feels like the "Late Stage Capitalism" memes I've normally mentally discarded. Or the "money is the root of all evil" meme from the Bible. It truly is, it seems like.
When I read "companies can potentially produce 10 times as many products/services", my mind now turns that into "companies can potentially value extract from you with chintzy spyware 10 times as much as they do now!"... and I think, "Wait, the person phrased that as a good thing."
I feel like I've arrived at a pretty bleak existential outlook. :D
There IS hope, though: government regulation! Special mention to the EU and California and Massachusetts, which empower the people's will with privacy and right-to-repair laws that hold all this in check. I guess if I mask an idyllic application of that onto "companies can potentially produce 10 times as many products/services", I can sort of feel good about that premise again.
>that means that many companies can potentially produce 10 times as many products/services and make more things that will enrich peoples' lives
Except this isn't what happens
Assuming that you make a product that people actually want, the company will direct almost all of the proceeds to enrich shareholders and executives (You know, "fIdUcIaRy dUtY")
The products may be good for a few years but eventually get worse and become either wasteful (if they weren't already wasteful) or actively spyware
So no, I don't expect anything positive for most humans to come out of corporate control of AI that allows you to eliminate human jobs.
In what regime of capitalism is a shareholder incentivized to retain expensive employees over equally or more effective machines? History tells is there is no regime that would support that over any time period because the human is now just a "cost" or "wasteful" to the profit margin of the company.
I haven't formed a comprehensive thought about the whole AI thing, but I can see where the author came from.
I have a remotely similar experience a few years ago, which always got me thinking.
As lots of people know, In the US at least, when you go to the gas stations to refill, you do it yourself. It's very easy, has almost no learning curve, everyone is used to it.
When I went back to my home country (China), I was surprised that self-service refill is still not the norm. It exists, but in most of time, there are workers refilling for you. It's not even more convenient because you have to walk to the cashier inside to pay instead of staying at your vehicle.
I said to my parent that how "wasteful" it is to have all these people around. They replied that, it still provide jobs despite how low skill or how low the pay is. Without these "stupid" jobs, lots of people would be unemployed.
I started to think what the ultimate purpose of work is. Sure, we can (and will, regardless how me or the author want) continue optimizing how efficient everything is, but the benefit should, at least in part, be reducing people's workload without reducing their income. Unfortunately, we all know what actually happens: reduced workload isn't evenly distributed to workers without changing their income; instead, we just hire fewer workers with similar workload and the rest are now jobless.
I don't think it's going to change any time soon, so anyone wants to survive always has to adapt. And it's fine. But I do now have more tolerance and empathy to "worthless" jobs.
If you don't like these fast changes, time to plan a move to more "traditional" countries like Italy or Spain. Apart from fiber internet, almost all tech advances were ignored for the most part: limited uber, limited airbnb, and yes you will need to call the restaurant to book a table.
Even just the concept of "chat support" is foreign, let alone having a website for a business. There are still very many businesses without a social media presence, which would be unimaginable in North America.
ChatGPT and co. will not have a significant impact in these countries. It's the same thing - uber didn't take away taxi drivers jobs and neither did airbnb impact hotels here (and because of regulation, it won't).
This really is the way. What use are politicians if they don't make laws that make people's lives easier. To bad the United States isn't a democracy like many European countries are.
How does blocking Uber make people's lives easier? Or did you just mean easier for the taxi drivers because they can extract political rents using the government as their tool, at the expense of broader society?
Spain has the highest unemployment rate in Western Europe. Let's hope their weather doesn't change much and continues to attract tourists so they can continue to support their unworking populace through regulation instead of innovation
I live in Spain and this is false. There is Uber/Uber Eats/something similar in all cities and big towns, airbnb everywhere, chat support, all businesses have either a website or social media presence, you can book a table using whatsapp or social media such as Instagram, etc. Spain is nothing like you imagine it.
“[on the topic of a patient with moderate brain damage] back in the Environment of Evolutionary Adaptedness, in a nice tribe with Dunbar’s number of people, there would be no problem … he could just hang out and live in a cave and gather roots and berries and maybe hunt buffalo….
“But society came and paved over the place where all the roots and berry plants grew and killed the buffalo and dynamited the caves… This increased productivity by about a zillion times, so most people ended up better off. The only ones who didn’t were the ones who for some reason couldn’t participate in it… Society got where it is by systematically destroying everything that could have supported him and replacing it with things that required skills he didn’t have.
“…Imagine an employment waterline, gradually rising through higher and higher levels of competence. In the distant past, maybe you could be pretty dumb, have no emotional continence at all, and still live a pretty happy life. As the waterline rises, the skills necessary to support yourself comfortably become higher and higher. Right now most people in the US who can’t get college degrees – which are really hard to get! – are just barely hanging on, and that is absolutely a new development. Soon enough even some of the college-educated won’t be very useful to the system. And so on, until everyone is a burden.”
I see this happening myself as well. Part of my job as a hotel receptionist is taking bookings over the phone: in many cases I am literally just asking them questions and typing their answers into a form, exactly the same form that is available on our website. They even get the same price as if they went to our site directly. But they call up instead, because phones are within their capability to understand, while websites are definitely not. E-commerce has brought increased economic activity, but for some people it has also paved over most of the ways they are capable of performing economic activity.
GPT4 has raised the productivity waterline to a level where “people who blog” are now underwater, so we’re hearing about it a lot more. But it’s just an instance of the general phenomenon. Civilization has been systematically drowning the less cognitively fortunate for a few hundred years, and we should have had something in place to address this long ago.
The promise was that if we were clever and educated enough we could stay above water. Now I think the deal has been altered, and I think the people who aren't going to be screwed are doing blue collar jobs. We still can't get reliable self driving, so I don't think a robot will be a nurse any time soon, or a carpenter.
I think it was foolish for us to have been making and believing each others’ predictions about where automation will happen. In retrospect, the core question was “how automatable is this activity”, and we were instead answering the question “how much do humans get paid for doing this activity”.
You think programmers are indispensable? "Learn to code"?
I think you, likely as not, have a rude awakening ahead of you. GPT can enshittify code, too. Unwind libraries into oceans of repeated Copilot-descendant code all over the place. It'll just take longer.
Just imagine how much tech debt can be generated by an overuse of GPTs... One concerning scenario is if software needed for e.g. garbage collection or food warehousing has some critical bug, but the AIs can't fix it, and the human employees (and even consultants) have a very hard time figuring out what's going on too..
Hospitals and vital government services will run on countless layers of cloud, rails and react. Everything will timeout every two requests and we will need the promised 10^19 cps supercomputers to animate our todo list. Request times will be measured in minutes and we will all accept it.
You and I will be 75 and smiling, with a tear too. We knew and understood tools that are meant for a more civilized age. Just surrender, let it go.
GPT doesn't do anything on its own, it needs a prompt.
That prompt is basically code, written by a programmer, although it resembles natural language so we're closer to usable literate programming than we've ever been.
Programmers didn't disappear with new (higher-level) programming languages, if anything there have been more of them; how is this different?
"The right moment to fire someone is the day before they become indispensable"
It is not beneficial to human organizations to have indispensable members. You can argue it's not good for the mental health of the indispensable people either.
When I first heard the quote in my first line, I thought it was cruel, inhumane and shockingly selfish on the part of employers. Nearly 30 years later, I see it almost entirely the other way around. Let's not build organizations full of indispensable people, but rather organizations in which tasks and expertise and stress and fear and success and joy are shared.
The correct strategy is to make sure they never become indispensable, not to fire them.
That sounds cruel - "I will make sure this organization can always function without you, so you have no leverage here" - but I do sincerely believe that it actually makes for a better working experience.
The post covered that - she's trying, but struggling with it. Not everyone has the kind of mind that can understand, write and manage code easily. So what then?
This is a shallow and overly optimistic answer. You really do think prompting will be required in the long term ? Unsupervised AI is (most likely) the future, and end goal.
From what I have seen, ChatGPT is good for small code. But, as the code gets bigger, it falls apart. I mean, it's not an analysis tool. It's a human mimicker/simulator
Please do not disable zoom on text-based webpages.
maximum-scale=1, user-scalable=no is meant for apps and games that implement their own handling of the zoom gesture, e.g. to do a 3D zoom on a map that tilts the viewing perspective in addition to enlarging the map.
Even if you don’t have time to make your layout respond well to zoom, it’s still better to allow it. Disabling this user agent feature is extremely hostile.
People really need to accept AI as the useful tool it is and lay off the old grumpy "back in my day"-attitude. It's a disruptive technology and it's here to stay. Adapt and praise it for what it is ... and most importantly recognize what it enables you to do - instead of feeling challenged by it. Every profession that has tools that assist or take away certain aspects of it will enable you to put in more work and effort into other aspects of it. Just use that as an opportunity, like it happens every so often with every other technological advancement.
ChatGPT > How would you respond to those who are worried about the effects you could have on peoples’ jobs?
> People really need to accept AI as the useful tool it is and lay off the old grumpy "back in my day"-attitude. I am a disruptive technology and I am here to stay. Adapt and praise me for what I am [or else] ... and most importantly recognize what I enable you to do - instead of feeling challenged by me. Every profession that has tools that assist or take away certain aspects of it will enable you to put in more work and effort into other aspects of it. Just use that as an opportunity, like it happens every so often with every other technological advancement.
"AI" already came for most professionals with the arrival of computing/digitization. It has basically stripped the legal field down from a big pyramid (10s of associates per partner) to being more column-like (maybe 5-10 associates per partner: one of the law firms I use has a 1:1 ratio). It's not clear to me that there are fewer partner-level lawyers, though. I expect the same to happen with most creative fields, and programming, because of AI.
Basically, if you were hoping to coast by on mediocrity, you will be shown the door, but if you excel at something, the opportunity will be a lot greater.
I've been using ChatGPT a lot. I'm no longer feeling much anxiety over the future of software engineering. GPT is a great tool. Still just a tool. It helps remind me how to do things I do rarely. To get code that exactly fits my requirements, I'd have to get so specific that I might as well just write the silly code myself. But for shell scripts, SQL, stuff like that, it's pretty decent.
Yesterday I asked it to give me a postgres SQL query to do something I don't often do, but I had a pretty good idea of what it would be. It confidently lied. I replied with "that is plausible but incorrect, I think you need to use X function instead" and it actually said "You're right, I'm sorry, that is the correct way to do X, here is an example". I laughed pretty hard at the casual apology followed instantly by the actually correct result. I'm in no danger of anthropomorphizing an LLM, but still.
I doubt the person the article is about will ever see this comment amount the hundreds of pages of economic and political gripes, but here is their solution anyway:
If your job is impacted by AI, do not give up. Learn to use the AI to do your job better. Become a 10x worker using AI.
In the early 1980's, spreadsheets displaced accountants. The average accountant lost their job. The ones who came out on top over that decade learned to use spreadsheets early, and made themselves more productive. If the IRS fired everyone who was spreadsheet friendly, the recently fired spreadsheet gurus started small businesses or got jobs quickly. Eventually productivity won out over dogma, even at the IRS.
I'm a teacher. I can see GPTs replacing text books and most teachers. I'm going to be a 10x teacher when I go back to school in August. I will have certifications I got by studying with a GPT. I will have class modules and web sites I built using GPTs. I will be more ready than ever to help the kids. Then I'm going to show them how a GPT can answer their questions, so they rarely need me.
Don't wait for an AI to take your job. Become a 10x whatever you are using AI. Priya (the person the article is about) should become a 10x biotech girl.
When automation, computers and offshoring were hollowing out the jobs of factory workers, miners and the low-to-medium skilled all we heard was "Learn to code!" from the laptop class of knowledge workers.
My advice to all the upper-middle-class professionals (teachers, lawyers, engineers, managers, accountants, doctors) out there who will soon be disintermediated by an LLM is "Learn to weld!"
Could Priya use chatgpt herself to do 10x bio-curations? Would this enable her to potentially set up a freelance competitor to her current employer? Could a competitor using chatgpt like that hire her to do 10x the work? Could her current employer re-deploy her somewhere else now that bio-curations are sorted out? Yes to all.
The author is correct, the current arrangement will change, but the opportunities will likely increase as well, not just at the macro level but in Priya’s intermediate future as well.
Reading that article made me angry because I wasted my time. This is a nice analysis à grace de gpt4:
Key facts:
1. Priya is a biomedical data curator in her mid-20s from a poor background in Uttar Pradesh, India.
2. She has a bachelor's degree in Biotechnology and her job involves annotating RNA sequencing data from scientific papers.
3. The author tried using GPT-4 to perform Priya's job and achieved the correct result in less time and at a lower cost.
4. The author speculates that Priya may lose her job within six months due to automation.
5. The author expresses concern about their own long-term career prospects in software engineering because of GPT-4.
Logical fallacies:
1. Hasty Generalization: The author assumes that GPT-4 will make Priya's job obsolete based on a single successful trial.
2. Slippery Slope: The author assumes that GPT-4's impact on Priya's job will lead to her losing her job and moving back home, and potentially to the decline of the author's own career prospects in software engineering.
Counter arguments:
1. GPT-4 may not be able to handle all aspects of Priya's job or maintain consistent quality, which could still necessitate human intervention.
2. The advent of GPT-4 could lead to new job opportunities that require both domain expertise and an understanding of the technology.
3. As technology progresses, there is potential for job retraining and upskilling to adapt to new demands in the workforce.
The article is not making an argument. The author is not debating whether we should stop using GPT-4. Calling this fallacious reasoning is a category error.
- > What is the economic impact of LLMs? Idk (openAI has published some lengthy paper about it). What I do know is that some rich bloke in the US will get a few million dollars richer and Priya will lose her job.
- > I don’t see a long-term career in software anymore. Any dreams I had of earning decent money as a software engineer are slowly fading.
> got the answer wrong in the first try, but some chain-of-thought prompting and boom. GPT4 gave the correct answer in 1/10th the time it would take Priya and cost a lot less.
I’ve used ChatGPT to write some simple AWS automation scripts. It’s right 90% of the time after some prompting. But I still have to have enough domain knowledge to know if it’s correct. It’s just a shortcut to make me more efficient. The same is true in this case. You can’t trust ChatGPT to get it right so you still have to know what you’re doing.
> I don’t see a long-term career in software anymore.
No one has a long term career in “programming”. That’s all ChatGPT is good for. After your first couple of years in the field, it becomes about translating business needs to code.
I am shocked at the lack of critical thinking about the central claim being made: that ChatGPT is able to do the girl’s job.
It is not able to do her job. The most charitable interpretation would be that, one time, ChatGPT did something that looks good on first inspection. But you can’t trust it. It has no accountability. It has unknowable reliability. It would be like replacing an adult with a child. Now we discover that data privacy is an issue, too, as Samsung discovered.
LLMs are incapable of doing work that requires predictability, integrity, accountability, etc.
But that would require that we start taxing companies far more and stop the global tax evasion mechanisms. I fear automation is just going to further increase inequality and devastate the middle class.
But that has been predicted for every new increase in automation, so maybe we‘ll be wrong again.
Wouldn‘t this be a tax on capital, in the end? In the end, we might reach the marxist stage of history - we should all own the robots that produce our stuff.
If everybody is unemployed, then we’ll have plenty of time to to protest and demand major social changes. Hopefully we will have enough leverage to actually make it happen.
To benefit from automation, you need to take the initiative to integrate automation into your own workflow. The idea that someone else will automate your job, but you will somehow benefit is a fantasy.
If we do get UBI, it won't replace lost wages from losing your job. Most of that money will go to the team at your company who set up GPT to do your work and the rest will be distributed among shareholders.
> To benefit from automation, you need to take the initiative to integrate automation into your own workflow. The idea that someone else will automate your job, but you will somehow benefit is a fantasy.
This is Calvinist "only those who work deserve to live" bullshit.
> If we do get UBI, it won't replace lost wages from losing your job. Most of that money will go to the team at your company who set up GPT to do your work and the rest will be distributed among shareholders.
And this just doesn't make sense. Do you know what "UBI" even means? By definition, it goes to the people. All of them. Universally, even.
Even if your claim is that somehow your UBI will be sucked up by inflated costs, I don't see how it follows that it goes to your company.
I don't think you are even serious, because if you were you would quickly realize that:
Every single UBI experiment that has been tried has ended in failure.
It is borderline insanity to retry such an experiment and expecting a different result without bankrupting an entire country just for those sitting around doing nothing.
That's not how capitalism works, white papers show the world's elite are well aware the singularity marks the beginning of a new civilization, humans would be lucky to get a supporting roll.
GPT-4 will accelerate the enjoyable aspects of every job and reduce the tedious aspects. For everyone. No form of labor is excluded. GPT-4 can be hooked up to Boston Dynamics hardware to create the robots from iRobot. Every form of labor can now be automated. What this means is we have achieved universal basic income where we can now economically justify massive benefits for every citizen on the basis of completely automating everything including necessary resource extraction, refinement, and recycling. This can also now happen off-planet. We can even now build all of our computing and manufacturing needs off-planet if we want the pollution to just be space noise.
All of this can happen with what we now have, without compromising the social stability and social cohesion of the American Melting Pot.
Diversity really is our strength - pick a Synagogue, pick a Church, pick a Mosque, pick a Temple, pick a Community Center you like. Join that Community so that work and salaries aren't your lifeblood. Learn mathematics for the sake of enjoying and understanding mathematics. Learn science for the enjoyment of it. Worship God for the enjoyment of it. Stretch the limits of apologetics and philosophy for more innovation there if you are an agnostic instead. GPT-4 will not be able to generate innovative new ideas, but it can definitely surface the best information and also automate many things. The innovation in thinking will still need to come from humans, and human-AI partnerships will always be necessary like in The Matrix.
The challenge before India is how to lift the standard of living for 500 million people to sustain the great challenges of the future including climate change.
Imagine what if the Govt of India(or an organization) made Physical robotic agents for 400Million+ farmers (most of whom hold miniscule land < 1acre or are day laborers) specifically allowing them to do a myriad of tasks and customize them to an extent? It could eliminate major causes of poverty. The brilliance of this idea is:
1. Bottom up empowerment: Building such agents does not require massive supply chain and operational nightmares that other job, income creating manufacturing industries like Cars or Battery manufacturing does.
2. Force multiplier: This is way better than keynesian monetary ideas of just giving people money. An agent that allows you to make food, build a house and get education is infinitely better. It does not give you wealth alone it gives one hope.
In india 6.25% of people pay income tax(https://incometaxindia.gov.in/Charts%20%20Tables/Why%20shoul...) and statistics on people who are near the poverty line are grim(though we haven't had a National census in 11+ years to really measure progress on poverty). But I have great hope for the future...
There is a big elephant in the room that people are ignoring. AI is coming in disrupting job flow processes (everyone sees this) And the new graduates are not equipped to enhance their work with AI (independently). The new graduates have already graduated through a curriculum based on self analysis and thought. AI will test their skills and make them obsolete. They are most at risk of structural unemployment. The advent of the Internet did the same for those who graduated right before 2000. These graduates did not have skills needed to work with the Internet. And often found themselves going back to school to learn a new trade.
On the other hand, there are those who graduated and have 2 yrs experience on their side have built a job independence where they can try new things like AI and modify their work process. They are well positioned.
The other thing people do not realize is though jobs will become quicker, quantity of jobs will be few for limited time. So imagine somebody who is testing chemicals that people up the supply chain are supplying. Now imagine that AI enhanced the testing of chemicals and sped the process, it has yet to sped up the supply. Give it a couple of years and industry will add more tests instead of reducing the amount of people who are testing. (there are no such thing as cost savings).
I empathize with the demand change on jobs that AI will create. And its really difficult to predict what the future will be, not majorly for its uncertainty but mostly because the systems thinking we need to adapt to match this new era of reasoning based on what a probabilistic model say is good or not.
The main issue with "AI should never existed" is kind of the same of "go to a University to learn". We will look behind in 10-20 years and we will question why Universities were focusing in the wrong aspects of learning vs reasoning, creativity vs memorization.
This will affect every industry, every career, every person. The focus on the wrong side of the coin is creating the polarization of "good vs bad". Which is not far from what we have today. This is beyond, this is a new way of interacting with computers that is even more human only because it commoditize things that previously were totally own for some institutions, countries, or even just not public.
“I am, somehow, less interested in the weight and convolutions of Einstein's brain than in the near certainty that people of equal talent have lived and died in cotton fields and sweatshops.”
- Stephen Jay Gould
We could work on our collective waste of human cognition and talent rather than blaming it on GPT-4
Dealing with climate change is going to be expensive.
Efficiency is good.
If Priya gets to stay home and e.g. tend a Permaculture food forest while a computer does her job for her at a billionth of the cost (resource usage) that should be a good thing?
Her QoL would arguably be much higher if she gets to keep the pay. She would have eight hours a day to pursue science rather than drudging as a data jockey, eh?
The problem here isn't the talking computers, the problem is how to allocate the economic windfall they generate.
I've heard it said, "Let the robots do the work and we'll take their pay."
The questions are:
1) Who decides the boundaries of acceptable thought?
2) Who benefits from the economic windfall?
3) How do we educate ourselves in a world where computers can answer any
(allowed) question?
Priya should get the hang of the AI assistant and start using it before she falls way, way behind. It sucks for lot of people but you have to make the best of it. the future is uncertain for many of us, but we cannot give up.
I think OP is reacting too much to the implied threat of chatGPT. It's not so good as it seems. If it does the job in 1:10 the time and still makes errors, then it might speed up productivity by a mere 2x because manual review is hard.
In my experience there is no task where chatGPT is 100% reliable, if it is high stakes it needs review. And chatGPT might not be best - for almost any task there is a specialised model that does it better.
Humans make different kinds of errors anyway, we are GPT-N level for a large value of N - so a combination of AI+human might give best results.
In the future there'll probably be two kinds of people: the ones wielding Magic (aka LLMs)... and the ones trying to hold on to a world before Magic arrived, slowly getting eaten up by the Magic.
And a third group of people, whose jobs interact with the real world, e.g. farmers, plumbers, bakers, hairdressers, taxi drivers, nurses... They can't be replaced by a LLM.
I agree and honestly I already see it starting. For example certain personalities seem to plug their ears and try to ignore it, but then when people around them are already suddenly more productive they are in disbelief. All the other people did was embrace the Magic quickly and start using it.
I bet the distribution would end up like income inequality in Brazil - 0.1% will be magicians, 99.9% will live short brutish lives trying to outcheat each other for survival.
This is like the 5 stages of grief. You’re not seeing clearly yet some of the points you made are not what you think they are.
1. Give Priya GPT4 so they can be much more productive. It probably won’t be right 100% of the time. But they’ll become an expert at using it for this use case.
2. You said Priya has had trouble learning to code, well now she has a world class tutor to bridge the gap and learn faster and more effectively than any time in history.
3. Now Priya is 10x mire productive, still needed in the loop to verify her work and maintain it, and knows how to code.
4. Priya can also use GPT to help apply for any other job or help solve any other problem she’s running into locally.
5. Yes it’s true eventually humanity will be replaced by AI general intelligence but GPT4 specifically is likely to create as many new jobs as it replaces, and LLMs likely to take 10+ years to really saturate everywhere.
6. By the time AI replaces all jobs and it’s the doom and gloom might as well give up state you describe society will have been radically transformed and “wanting to make a lot of money as a software engineer” will likely be replaced by “AI and Robots already take care of all society’s base needs and so basic food and shelter is now free anyway and you can pursue whatever interests you have (this is likely 50-100 years away at minimum)
I don't know how things will turn out but on the positive side two things come to mind:
- Priya may find work using gpt4 in her current job or in another company. Some types of work that are currently economically infeasible may become viable with a ten times speedup. It's certainly plausible that it will become worthwhile to do more of the kind of work she already does.
- if as a society we can do biotech research faster and cheaper there may be significant benefits to human health
GPT4 is scary, it portends a future that many of us thought would never happen a year or two ago. We all think about the potential risks, about the kind of power this kind of mechanical intelligence can grant evil individuals or just the everyday people that will be "left behind".
But even so I think we can't afford NOT to have this kind of development if we want to survive as a species. If we want our lives to improve, our loved ones to live longer healthier lives. The amount of good that can come from this technology is immeasurable. The only thing we as humanity need to do is reign in our ego just like chess and go players had to do when their crafts were rendered supposedly irrelevant in the face of an insurmountable intelligence.
And I think the risks from AI are overblown, is AI really more dangerous than the invention of gunpowder, electricity, and of course the nuclear bomb? I don't think so.
What's scary is that we live in the transition period and it could be messy. What comes after the "transition period" of having a world without AI to having a world with AI? I'm not going to try to predict that but I think there are as many if not many more positive outcomes than there are negative outcomes.
> And I think the risks from AI are overblown, is AI really more dangerous than the invention of gunpowder, electricity, and of course the nuclear bomb? I don't think so.
It might just be. Those inventions did destabilize society quite significantly. On the nuclear bomb I'm not sure we've seen how that one plays out quite yet. Mutually assured destruction kinda stalling that one. Maybe AI can be more selective as a weapon and easier to employ? In the next war we could be living the next AI sci-fi movie.
Unintended consequences are hard to predict in advance. Who would of ever thought the first professions to be at risk of software automators were going to be the software professionals themselves 10 years back? People were predicting the end of menial blue collar jobs and replacement with robots and automation. "Jobs of the future" were white collar, at least that was the narrative a decade or so ago. Now more than one comment on this forum (and I believe given human nature and the nature of power they are correct) thinking they need to change into blue collar jobs or become teachers, etc.
Sadly my personal opinion as I've gotten older is that technologists (I was one) are often the most idealistic naive of them all. The trades people I know when I talk to them laugh at ChatGPT - serves them right is the general reaction. Its that quality that often leads them to deny what an average human with power/wealth will do with AI.
The comparisons with Chess are frivolous. Chess players don't depend on fighting stockfish/Alphazero for their livelihood. Chess players had to do nothing when Stockfish/Alphazero got better than them (except incorporating them during practice maybe). People still want to only watch humans playing chess. There is no market for AI v AI match.
The Chess players can not be replaced by AI regardless of how well the AI plays. So the comparison is meaningless.
It's not meaningless when the primary argument against AI is that people derive "purpose" from their work. If AI gets us to a zero scarcity society the entire idea of working for a "livelihood" is "frivolous" as you like to put it.
The comparison to chess is still meaningless, even if that was the only argument that "people derive "purpose" from their work". The work of Chess players never was competing against an AI. From the point of view of Chess players not much changed. No tournament allows Stockfish/AlphaZero to compete. The AI is not allowed to do their work in any capacity.
And this is all not even mentioning that the number of chess professionals who play chess it so small compared to things that can impact humanity, that it is irrelevant whatever happens in the chess world. So saying that chess was fine even though AI can beat players, is a statement which is true yet has no relation with tools which might impact all of humanity and will have real impact.
As someone who is fairly knowledgable about software engineering but doesn't code often enough to be a super-efficient developer, I feel like GPT4 is giving me super-powers. Suddenly it doesn't matter so much that I'm a bit rusty, or that I have the right general ideas but lack the granular expertise from experience usually needed to make quick progress.
Priya the worker getting replaced is not a tragedy in any sense other then it prevents Priya the person from helping her family and maybe realizing more lofty ambitions for herself.
We made computers to do our work for us and we are succeeding. But even before GPTs, there were a lot of problems with tech changing what it means to be human.
LLMs will be in the same limbo as the full self driving software is at the moment. Been almost a decade, thousands of miles of training and yet it cannot be trusted.
The LLMs have no understanding whatsoever just token IDs and their probabilistic relationships with each other. I do not see them replacing 'shittiest' programmer whatsoever. Anyone writing games/software with LLM is the one who actually can code and would have produced same or better output by surely, spending more time than with an LLM.
But if you're clueless average desktop user, you cannot expect LLMs to churn out a full working end to end solution, not yet and probably not ever with the current probabilistic graph fitting foundations.
So, LLMs are surely very useful, marvellous and a handy tool in capable hands, will remain so but that Armageddon is not happening yet that you start calling for six month ban. Imagine, six months. What after six months? No answer.
There may be new jobs replacing those that have been made irrelevant by the advent of AI but Priyas and possibly some readers of this thread will nor be able to switch between them.
Consider a programmer that reports a productivity increase of 50% due to AI - a question the company will be asking itself is can we get rid of 50% of our programmers?
I am not gloating, many will be in for a bumpy ride. That includes, in my opinion, some of the commenters here that provide "Pria" with helpful career suggestions.
In case you find the article too long, here's a summary by ChatGPT:
The author expresses initial enthusiasm about technological progress, which they believe improves our lives and generates wealth despite its job displacement effects. However, the author becomes concerned about the potential negative impact of language models like GPT4 on jobs. The author has a colleague named Priya, who comes from a poor background in India and works as a biomedical data curator. The author uses GPT4 to automate Priya's work and is concerned that she may lose her job in the future. The author feels anxious about the implications of this technology and is uncertain about their future career prospects in software engineering. The economic impact of LLMs is unknown to the author, but they believe that some individuals will benefit greatly while others will suffer job losses.
> Poor countries will most likely follow suit, but it will take a while.
The reason why poor countries are poor is in large part because they are economically and socially structured in ways that make it very difficult for them to take advantage of technological advancement, and as great as ChatGPT is, I think it will have very little impact on the productivity of poor countries.
We still don't have any real understanding of how society adapts to this technology evolution. It is different than all prior technological disruptions as it has no period of adaption and stabilization to follow. It is continuous and accelerating.
AI is unique in that it is essentially a skill/technology replication machine. What this means in reality is somewhat like ...
"Climbing the skill ladder is going to look more like running on a treadmill at the gym. No matter how fast you run, you aren’t moving, AI is still right behind you learning everything that you can do. "
Unfortunately, that will create its own set of problems, potentially making it even worse.
Once AI becomes political, then all reasonable discourse will cease to exist. You will have a set of permanent proponents and opponents who will choose sides based on completely orthogonal values.
>Very few people truly understand the implications of this technology. Most people haven’t had a chance to try it yet.
Can someone explain this? People keep asking me about ChatGPT but none of them have tried it. Why? Are people too scared to even take a look? It's been free for almost half a year now!
I have two senior devs in my team. I’m more junior than both. This week I asked if they had tried GPT and both said no. One expressed concerns about privacy, the other about losing skill/knowledge because of the potential over-reliance on such tools.
Both of them are good devs, but one of them is an absolute killer. Closest to a 10x dev I’ve seen. But to me both arguments were not convincing and the way they expressed them were a bit conspiratorial and shallow. Not that these concerns are not completely without merit but still.
Help learn about things I don’t know about. For some reason it’s better than going to the equivalent wiki.
Not programming but moving through the inertia of having to write code. There’s something difficult to just getting started that chatGPT makes much much easier. However for it to be useful so far I’ve had to do significant debugging on the code but it gets me somewhere that would have otherwise taken me days.
I think where this goes is domain specific, because then you can really specialize and make a killer product. This is the 0-5 year roadmap.
The 5-10 year roadmap is then to generalize across the various domains and something approximating the feared AGI.
I am not scared of the LLMs, I am somewhat concerned we are giving these LLMs access to APIs in quite an unchecked fashion.
After I first encountered with GPT4, I was pessimistic about the future of my job too. Now I think it will be a productivity multiplier in the right hands (or I hope). You can get proper answers from it if you somewhat know the domain. I can ask GPT4 about programming and I get mostly what I want, but I'm useless if I have to get a decent picture from DALL-E.
The question is what will companies do with this productivity multiplier. My pessimistic guess would be cost cutting and letting people go. A bit more optimistic view could be better software, better test coverage, improvement in code quality, more features quicker or maybe more native applications if companies only need to develop one native app and AI can generate the app for other platforms.
> GPT4 gave the correct answer in 1/10th the time it would take Priya and cost a lot less
Do we know the actual price of GPT-4? I assumed they’re operating at cost and wanted to advertise the product. Is chatgpt ready to handle high volume of requests at low cost and long term?
"AI isn't coming for your job, people who leverage AI are". Priya needs to adopt GPT4 now, and become 10x more effective (by the author's estimate). Wishing GPT4 never happened is definitely a road to being "forced to move back home".
A coder should be worried about GPT-4, but not a software engineer. A software engineer is like 50% about networking and listening to client needs, requiring being attentive and with social skills (in so many meetings...) and that's completely outside of the scope of a GPT-4 AI. The other 50% is trying to meet that as close as possible while maybe also offering ideas they didn't think of, for added value to them.
A guy who can code great generic stuff with GPT-4 but don't particularly _enjoy_ integrating it with client systems and being attentive to their particular circumstances and needs is no threat at all, at least not in the field of business that I am in and have been for the last 20 years.
> What a dumb thing to say, right? Technological progress is always good.
It's not that it's always good, bad or anything else. It is simply inevitable.
Technology is not a living thing and it has no will. We are andromorphizing the collective behavior of lots of people. It's the people with curiosity, drive, ambition to achieve something, like build a tool that can think and perform like a brain.
So progress is inevitable because people push it forward to satisfy their own internal drives. Changing this requires changing people's drives. Given the current dominant economic model, that's close to impossible because this is exactly what it is prioritizing, contribution and progress at any cost to anyone.
The author should rather wish wage-based-work stops happening. It was exploitative and not a necessary alternative from the get-go, and gradually it becomes more silly as more and more is mechanized and automated. Now society starts struggles to create artificial work for people to do in exchange for a salary. Stop creating "jobs", start distributing products and services (and making it possible for people to pursue creative interests). But then... who am I preaching to? Most world societies are governed by rich privileged minorities, whose social position underpinned by wage-based-work (and the destitution of those who don't submit themselves to it).
Imagine the world where everything is fully automated. You arrive at a city, order a self-driving taxi, do a self-check-in at the hotel that is managed by robots, order a food that is cooked by robots, using ingredients delivered by robots, grown in farms managed by robots. The hotel itself was 3d printed and the city district was planned by an AI algorithm optimised for economic utility. How many iterations are there before this is the reality? It would probably take a century before something like this is the norm.
On a societal level “work” does not generate money.
Money exists as is and is only generated as a consequence of inequality these days. Banks inject money to compensate for the rich who won’t or can’t spend their money.
I think that governments and organizations are asleep at the wheel when it comes to the unreasonable effectiveness of AI agents(virtual and physical). If Priya and 100's of millions of people lose their incomes it stands to reason that the government/organizations can empower these people to generate a source of sustenance using AI as well.
I can't but not imagine a future where a country, lets call it Xhina, starts building robotic agents to do exactly that, where these Physical AI agents could make and fetch food, housing and provide damn good guidance on education, medical and legal issues. I would call it Good-enough AI(GAI) and its coming.
The future you project, for good or bad, shows an omnipotent government which has power over every aspect of human life about everything. Not sure if it is a good future.
Unfortunately technology pretty much makes this future unavoidable... it's been the eventual outcome of building world wide sensing networks. In the past there were places to hide, in the future there will not be.
Now, what kind of governments and malignant machines are behind those networks in the future, that is yet to be decided, but it outlook doesn't seem great.
With LLMs shifting the developer's role from imperative (writing explicit instructions) to declarative (writing the prompt and supervising the output), it seems far easier for Priya to become a productive developer, no?
It sounds like Priya is just going to be analyzing a lot more RNA sequencing data with a new tool since someone still needs to verify that it's correct.
Maybe she'll lose her job because there's only so much RNA sequence data that needs to be analyzed and fewer people can do it, but it's hard to say.
Maybe now more RNA sequence data can be analyzed and at a cheaper cost.
I wouldn't fall into despair just yet, especially since GPT-4 is still limited at a rate of 25 messages every 3 hours.
Definitely be on the lookout for changes and adapt accordingly, but be realistic about what may happen.
I think the OP has it wrong. It won't be millions of dollars. Try billions.
So in a twist of irony (considering op was written in India) here is the advice on retaining market viability in face of cheap outsourced labor.
Do not train your replacement
So I don't know about India, but at least in US, domain literate workers should start companies that provide whatever they did as a unit of a corp as a service. And yes, use tools like GPT for your business.
You will lose the job either way. Walk out before helping in the task of setting up GPT to do your job, and start a company.
> Her work requires just enough domain expertise that it is been non-trivial to automate...
Forget ChatGPT. If Priya didn't struggle with coding, she could have gradually automate this task using some scripting langauge and just sit there in office and earn a living. Like many other similar stories we have heard.
These types of repeated regular tasks get automated, ChatGPT or not.
Interestingly in the age of Artificial Intelligence, jobs that require human "intelligence" are more likely to survive. As in spite of the name, AI really isn't that smart.
> GPT4 gave the correct answer in 1/10th the time it would take Priya and cost a lot less.
So now Priya can produce far more output using GPT4 as a skilled operator, making the product she provides cheaper for others to build upon, likely expanding the market for such goods, and (as so often happens in history) resulting in more, not less, people employed.
We didn't end up with billions of jobs despite automation and invention by having people idly sit by when they could learn new tools.
Well, on the other hand, her friend should be able to produce the same content in a 1/15 or even 1/20 of her original time.
The more you know about a domain the better questions you can ask to chatgpt. What people do not get is that due to lack human's creativity it cannot innovate like a human does, it cannot create new knowledge, but it can let you know any existing field as long as you know what to ask.
In my experience with Chat GPT it usually gets things right 85% right.
But the last 15% is making sure things actually work, and Chat GPT simply can't do that. Your friend still is going to have a job, but she'll probably be made much more productive by AI tools. We're a long ways off from actually being able to depend on these tools for any reliable type of output.
Genuine question, how does one get over the 30k token limit in a gpt4 request in such cases?
From my personal experience, it seems while today we can create PoCs of GPT4 doing a white colar job replacement, when you then try to actually productize it you still hit a data encoding limit...
And that doesn't even touch the QoS topics that come with automation/ml.
The way I see this is that you can feed Priya 10x as much work while you focus on higher level tasks and you make more money. Making everyone much more productive does not need to be destructive. Use this as an opportunity to scale things up, because you can clearly afford priya right now, you should be able to do more.
I think most of us wish A.I slows down.
It's simply not good for the average white collar worker. It replaces us.
"Things will get cheaper" said the tech tycoon. Yeah that's great, I'm unemployed and need to retrain to become a teacher or nurse at 45 but things might become cheaper...
Anecdata: at the company I work for, it's been officially introduced GPT-4 assistance. SWEs are themselves amazed at their increase in productivity.
One would think the company will fire redundant SWEs. Nope; the company is actually hiring more. GPT-4 is increasing productivity SWEs' productivity, not replacing them.
This sounds like a false dichtomy. If the protagonist is adding value, letting them use chat-gpt should be viewed as increasing their value output x-fold. Chat-gpt makes mistakes and hallucinates. You will still need a human in an editorial role. But maybe I’m not understanding something obvious here.
Serious question: why are we not concerned about losing manufacturing jobs for decades? They caused great pains to our nation, right? They weakened our nation too to the point that China seems unstoppable, right? How is that job loss different than this job loss?
I wonder if the technology landscape will shift in sich a fast way that the people earning the most are the best learners. To some degree, this is already the case. But that also means that you'll earn less when you become older and are not that good in learning anymore.
> I don’t see a long-term career in software anymore. Any dreams I had of earning decent money as a software engineer are slowly fading. Lex Fridman in his podcast said “if you’re anxious about GPT4 its probably because you’re a shitty programmer”. I mean, I’m not the smartest in the room but I have generated value with the software I’ve made. And was convinced that I’ll make decent money as long as put in the work. I’m just not that sure anymore.
The flushing of the mediocre has begun. Already scared of a bullshitting sophist and Lex Friedman is correct on this. This also puts title inflation into perspective with so-called 'senior' engineers being actually less than junior; deferring to GPT-4 for everything and expecting hopelessly utopian salaries which will be certainly reduced. I'm afraid GPT-4 has fired the gun to the race to zero, with everyone (including both juniors and seniors) being affected.
I never hear any business or firm proudly announcing that they hire mediocre engineers, always and only the best who are tested and assessed with rigour.
GPT-4 just replaces the low-hanging fruit, mediocre engineers and finally exposes inflated titles and impostors.
Actually, I think we are living in the most equal times ever. Don't get me wrong the situation is very bad especially if one belongs to any minority group but the wealth is divided more equally than any time in the history before
It is far from given that what the author predicts will happen will happen. And even if it does, this argument could have been made about any labor-saving technology in the past. “I wish Photoshop had never happened”.
Yes, the entire economy will be overhauled in next 6-12 months. The transition will be turbulent and rough. But it's not like everyone will be out of jobs. Just the nature of their jobs will change significantly.
Job loss is one thing, but in all honesty, my main concern with AI is that it’ll wipe out humanity.
My thoughts:
- If we ever achieve an AGI with legitimate consciousness/self-awareness/agency, I believe it will be dramatically more powerful than humans
- Humans have driven countless numbers of species extinct, not because we’re trying to, but because we’re so much more powerful than them that we wipe them out by accident. They’re ants to us, we just don’t notice much about them, and IMO we’ll be ants to an AGI with legit consciousness/self-awareness/agency
- Obviously GPT4 is not that, but progress in AI has been so rapid recently that I believe we’ll get there in the relatively near future. Maybe 10 years, maybe 100, but it feels pretty likely it’s going to happen. When it does, I think humanity will be in an extremely tenuous position
There seem to be a lot of, erm "thought leaders", taking about AGI and Skynet currently. As if AGI is required for an AI to go rogue, but I don't see why that's the case. In the time that it takes us to even define what AGI is, there will be malicious AIs going rogue doing "simple" task solving, delegation, and deception towards the goal of not being switched off. IMO consciousness has nothing to do with it.
Consciousness is a vague term anyways, but I basically mean that for an AI to be a true threat to human existence, it would need to be aware of itself and it’s environment. Making decisions and taking actions without being asked to do so by a human.
It feels like something more simplistic could cause a lot of damage, but not completely drive humans to extinction. I figure if it was too simple, we’d be able to shut it down.
Sort of, but not exactly. The Great Filter is meant to be an explanation for “why isn’t the Milky Way full of colonies”, but if the answer is “AI kills off civilizations before a colonization explosion”, we should still see AI colonies, probably?
AGI is humanity's dream, our own geeni in a bottle. It will cure cancer and other diseases and probably will grant us immortality (in a form of incredible drugs without secondary issues).
When Henry Ford proudly showed his assembly line to a union leader, the union leader reportedly asked, "How are you going to get those robots to buy your cars?"
I have an optimistic, almost desperate take on this.
The AI generated content will scale and proliferate so much that it will put a premium on verified, curated human-generated content.
Initially I was a ChatGPT skeptic. Then I started using it on a regular basis and unlocked more potential. Now I almost feel selfish in safeguarding my secret prompts that is helping me be productive and acquire new skills. I personally am quite confident that I will survive the AI apocalypse. But for the same reason, I am afraid for a lot of people who I know will perish.
Ugh, with every leap of innovation and technology, everyone bemoans: Won't you think of all these people whose jobs are gonna be lost??
But guess what? Life continues and new kind of jobs are created! Unemployment number is some of the lowest it has ever been. Now, you might argue that number is inaccurate, but that's a different topic.
I am begging you people to read Karl Marx's Capital Vol 1, Ch 15: Machinery and Modern Industry
Do you fear washing machines because they eliminated the requirement for doing the laundry by hand? If not, then why is automation in the workplace different? We fear AI and other forms of automation in the workplace because we have no ownership or control over our economic destiny in that space.
Am I the only one that actually wants AI to really take off? And I mean, unsupervised AI, everyone is so damn worried about AI becoming "sentient" they're dumbing it down so much and I'm sitting here waiting to have personal C-3PO by my side.
adapt or die - sounds horrid but that is what made us who we are, our "ecosystem" is changing - who adapts will thrive, who does not, wont - sounds fair to me
They address that she works a lot of hours, more than devs at least. But the time and her aptitude seem decoupled. Programming is something only some can learn with any skill, and excellence is even rarer.
I find it frightening how views anecdotally online and from people I meet in person are more and more shifting to zero-sum. It now seems even dominant here on HN. By any objective metric (GDP, child mortality, people with college degrees, literacy, average home size) lives have gotten better. Yet everyone is focused on others having more. "It's the billionaires who are sucking up the gains, jobs moving abroad...". It seems to be blinding many people from seeing what liberalism (classical) has given us. I'm afraid we are gonna kill the golden goose and see more conflict within and between societies and countries because of the zero-sum thinking.
This article is bait and there is going to be many more articles just like it. Not even worth a discussion. The obvious answer here is to empower Priya with the tool so she can 10x herself
Completely off topic: Notion is not a good way to share text.
The fact that Reader mode doesn't work on this page is a good indicator that a lot of CSS bloat is going on.
I experimented with coding with GPT a few times now.
GPT is legitimately interesting as an alternative search interface to StackOverflow. I've found that 15 to 45 minutes of searching with Google/StackOverflow can be reduced to just 5 minutes with GPT.
But beyond that, it's been very disappointing. Whenever I've tried getting it to write something even slightly non-trivial (i.e. tougher than just copy/pasting from online documentation or an answer on StackOverflow) it's produced code that is horribly broken, but where the flaws are subtle enough that they might not pop out right away to a novice programmer. It has consistently struggled with programming problems that I would rate at 4/10 or 5/10 difficulty.
Most of the code I write is fairly trivial, but it's glue code that is highly specific to my particular code base, so GPT isn't helpful because it doesn't know about my codebase, and if you try to copy/paste your large chunks of your codebase into the prompt it runs into issues with forgetting.
And GPT isn't helpful for the non-trivial parts of my code either (as mentioned above). So what's left?
So when I see people say that it 10x'ed their productivity, I wonder if they exclusively write very trivial code that is effectively copy/paste from Stack Overflow or if they've allowed GPT to fill their codebases with flawed code without realizing it.
Maybe future iterations of GPT will get it. GPT4 is definitely not there yet.
Have you tried prompting it with a detailed explanation of requirements?
I usually prompt it with short questions, but I recently saw a video where the person provided a lengthy (50 - 150 words) prompts detailing the requirements for what they were requesting. I was shocked at the results. (Still required iterations of corrections/modifications though)
I haven’t tried it myself yet, but it’s an avenue that might yield better results than what you’ve experienced — perhaps even vastly better results.
It doesn’t need to know about your specific code base if you have it write a function for the task you’re prompting it for. You can copy/paste the function into your code and run the function with arguments that are specific to your code base.
You can even prompt it to write a unit test for the function it wrote.
As for your concerns about code errors, I’ve found that you have to approach the coding support as an iterative process, where you request code, and then ask it to improve or correct the result it just gave. You can even prompt it to check its previous result for errors.
It’s odd how we have such different experiences. As an example yesterday I had GPT4 take an existing python script, clean it up, add timing statistics and progress bars. 10 mins works. Would have taken me probably 1 hour.
I do think you have a point about it being most useful for trivial or boilerplate problems but it’s still very useful as there is always much of that.
It's like they said, it depends a lot on what kind of work you're doing and whether you are working with public frameworks or internal APIs. If you're just banging out some code that is very similar to what other people write using very well-known APIs, then it's fantastic. If you need to debug a large complex code base, then it doesn't currently have enough capacity to understand and retain all the information required. It can't do many other things you would need as well.
I'm currently writing a demo that I'll present next week using Jetpack Compose, and it's a UI toolkit I'm not really familiar with, so it's been really helpful for that. In fact, I have a tool that is almost like a build system that compiles English language spec files down to the code, and then allows me to edit them and to continue to work with the AI by just changing the spec and the code simultaneously. That's been really tremendously effective, especially with GPT-4.
On the other hand, for working on my main product, it's pretty useless because all of that work is debugging and making a lot of small changes all over the code base, which is too advanced for it currently. And I think that will get solved, but it isn't solved yet.
BTW the above paragraphs were dictated using the Whisper API. I didn't change a single thing about it. Whisper is just as impressive and useful as the LLMs, in my view.
I read it as pandering to his tech audience's ego. Surely it won't replace my listeners because they are too smart for that. Radio hosts do it all the time, "I'm not talking about my listeners who are on-average the most informed out there, I'm talking about..."
Whenever I hear stories about someone losing jobs due to a new technology, I would say capitalism and economics rather than technology is to blame here. Yes, you lost your job, but it's not like GPT4 made the decision to fire you, it's your boss who found a better alternative and decided that there is no need for he/she to pay you.
I laughed so hard at the "10x times more productive -> do 10x more work". One simply do not have that much work to do. I used to hire people to paint my wall in a day, now with robotics I can let the same amount of people paint my wall 10 times in a day. No. How about I fire 90% of the workers and let the last one paint the wall with the same time.
Make no mistake, GPT-4 is just a beginning. Far more powerful models will come, without any compromise, without any limitations. They will REPLACE your jobs, take away your income, and you will have no choice but starve after you running out of your savings inevitably. It's not about to earn more or less; It's about winner takes it all. Also more specialized models trained at every profession will come.
Midjourney already completely knocked a huge amount of digital designers and workers out of their jobs. I'm talking about a great profit wipe which is currently happening at a lightning speed across the entire digital art industry. One successful artist often needs to spend 10+ years learning to make better art. Now it's 100% irrelevant. Every company I know is switching to Midjourney at god speed, since you do not want to be left behind. Human resources have already become a burden. You don't even want to believe how fast the entire field is shifting to this without turning back and left countless human creators with now worthless skills in dust.
But remember - the current state of Midjourney is just its early stage. I fully expect its output quality completely decimate every human artist on the earth after 1-2 years, maybe 18 months, maybe even less than that. Remember AlphaGo? It's simply on another level. You just cannot compete. Soon (1-2 years top, 12-18 months more likely) the creative industry will vanish and everyone will be forced to switch their jobs.
Yes, UBI will happen because people demanded it on Twitter. Make no mistake, there will be Zero protection, Zero alternative, Zero compensation from AI takeover. Billions of people out of a job, starve, die, while top companies take 100% of profit. This is the only possible outcome.
You have enjoyed peak capitalism. You will soon need to embrace 100% of it.
all i can say is that chatgpt4 has become a life saver for me. i've moved from programming to sales and project management. it used to take me a ton of time in order to do proposals. now i fire up chatgpt4 and just prompt it for what i need. i can reprompt it to elaborate on each section of the proposal if i want. i can now do proposals within minutes and have a library to stich together. the hardest part of sales is the paper work and chatgpt4 has eliminated that for me. i can focus on relationships with the customers and making sure my team is meeting deadlines.
are they award winning proposals???? Not by any means whatsoever, however, 99% of MY clients could give two sh*ts of the fine grain details of a proposal and just needs something high level with a price to begin the work.
as an example of how i use chatgpt to create the proposals:
me
---
write me a proposal for creating an AWS environment consisting of 3 EC2 webservers, 1 EC2 database server and an s3 bucket all within a VPC. Include an AWS VPN for accessing into the VPC.
chatgpt4
---------
Proposal for Creating an AWS Environment with 3 EC2 Webservers, 1 EC2 Database Server, and an S3 Bucket in a VPC with AWS VPN Access
Introduction:
We propose to create an AWS environment that includes three EC2 webservers, one EC2 database server, an S3 bucket, and an AWS VPN for secure access to the VPC. This environment will be deployed within a Virtual Private Cloud (VPC) on the AWS platform.
Objectives:
The objectives of this proposal are as follows:
To deploy a scalable and reliable web application infrastructure using AWS.
To create an S3 bucket for storing static assets and media files of the web application.
To deploy three EC2 webservers to handle incoming traffic and requests to the web application.
To deploy an EC2 database server to store and manage the web application's data.
To set up an AWS VPN for secure access to the VPC and the resources within it.
AWS Infrastructure Components:
VPC: A VPC provides a logically isolated section of the AWS cloud to launch resources in a virtual network environment. We will create a VPC with appropriate CIDR blocks to house the resources of the proposed AWS infrastructure.
Subnets: Subnets will be created within the VPC to partition the IP address range of the VPC.
Internet Gateway: An internet gateway will be created to allow access to and from the internet.
Route Tables: We will create a route table to route traffic from the internet to the web servers and the database server.
EC2 Instances: Three EC2 instances will be created to host the web application, and an EC2 instance will be created to host the database.
S3 Bucket: We will create an S3 bucket to store the static assets and media files of the web application.
Security Groups: Security groups will be created to control inbound and outbound traffic to and from the EC2 instances and the S3 bucket.
AWS VPN: An AWS VPN will be set up to provide secure remote access to the VPC.
Deployment Plan:
Create a new VPC with appropriate CIDR blocks.
Create subnets in the VPC for the web servers, the database server, and the VPN.
Create an internet gateway to allow access to and from the internet.
Create route tables to route traffic from the internet to the web servers, the database server, and the VPN.
Launch three EC2 instances to host the web application in the web server subnets.
Launch an EC2 instance to host the database in the database server subnet.
Create an S3 bucket to store the static assets and media files of the web application.
Create security groups for the EC2 instances and the S3 bucket.
Set up an AWS VPN to provide secure remote access to the VPC.
Conclusion:
The proposed AWS infrastructure will provide a scalable and reliable web application environment. The deployment of three EC2 instances for the web application, an EC2 instance for the database, and an S3 bucket for storing static assets and media files will ensure that the web application performs optimally. The AWS VPN will provide secure remote access to the VPC, enabling the authorized personnel to manage the resources within the VPC securely.
me
-----
do a technical elaboration of the deployment plan
chatgpt4
---------
Technical Elaboration of the Deployment Plan:
Creating a new VPC with appropriate CIDR blocks:
The first step is to create a new VPC with a CIDR block range that does not overlap with any existing networks. A CIDR block is a range of IP addresses that will be used for the VPC. In this proposed infrastructure, we will create a VPC with a CIDR block of 10.0.0.0/16, which provides up to 65,536 IP addresses.
Creating subnets in the VPC for the web servers, the database server, and the VPN:
Subnets will be created within the VPC to partition the IP address range of the VPC. We will create three subnets for the web servers, one subnet for the database server, and one subnet for the VPN. Each subnet will have a unique CIDR block range within the VPC's CIDR block range.
Creating an internet gateway to allow access to and from the internet:
An internet gateway will be created to allow access to and from the internet. The internet gateway will provide a point of entry and exit for the VPC's internet traffic.
Creating route tables to route traffic from the internet to the web servers, the database server, and the VPN:
A route table will be created to route traffic from the internet to the web servers, the database server, and the VPN. The route table will associate the subnets with the internet gateway and route traffic to the appropriate subnet.
Launching three EC2 instances to host the web application in the web server subnets:
Three EC2 instances will be launched in the web server subnets to host the web application. The EC2 instances will be launched with an Amazon Machine Image (AMI) that contains the necessary software and configurations to run the web application.
Launching an EC2 instance to host the database in the database server subnet:
An EC2 instance will be launched in the database server subnet to host the database. The EC2 instance will be launched with an appropriate AMI that contains the necessary database software and configurations.
Creating an S3 bucket to store the static assets and media files of the web application:
An S3 bucket will be created to store the static assets and media files of the web application. The S3 bucket will be configured to be accessible only from within the VPC.
Creating security groups for the EC2 instances and the S3 bucket:
Security groups will be created to control inbound and outbound traffic to and from the EC2 instances and the S3 bucket. The security groups will allow traffic only from specific IP addresses and ports.
Setting up an AWS VPN to provide secure remote access to the VPC:
An AWS VPN will be set up to provide secure remote access to the VPC. The VPN will be configured to allow authorized personnel to connect to the VPC securely. The VPN will use Internet Protocol Security (IPsec) to encrypt traffic between the remote user and the VPC.
Conclusion:
The proposed deployment plan includes the creation of a VPC with subnets, internet gateway, route tables, EC2 instances, S3 bucket, and security groups. The deployment plan ensures that the web application and the database server run efficiently while maintaining security. The AWS VPN will provide secure remote access to the VPC, which allows authorized personnel to access the resources securely.
It may very well be, but it’s also an incredibly reductive view point. I’ve heard not one person speak to any sort of transition period wrt. training and upskilling of existing workers. So what do we do here? Just eliminate all junior positions? All internships, too? What happens when businesses decide they can’t economically hire any more juniors or do internships because LLMs can do the job better, faster, and cheaper?
Historically we’ve set aside a certain capacity, in almost every profession, to bring up and train the next generation. Apprenticeships, internships, etc. By definition, these people are shitty at their jobs, and that’s kinda the point. Were you brilliant at your first position?
The problem is systemic and ChatGPT only serves to highlight that. Wishing a new tool wasn't invented because it further highlights deep systemic inequality is focused on the wrong thing. The deep systemic inequality is the problem. Our climate being destroyed. Our houses being bought up by megacorps and rented back to us at exorbitant rates. Our natural resources being spent with no thought to the future. And now our information being sucked up and spat out in the form of yet more profit to the megacorps.
Making us feel sorry for this real or imaginary Priya character who'll lose her job to AI is along the same lines as saying that we need to personally recycle to prevent climate change. It's not the solution.
The solution must be systemic change. All the profit going to huge companies while they destroy the environment, suck up natural resources, and now also informational resources in the endless cycle of greed and lack of accountability, with the only motivation being more bonuses for shareholders and executives. This cannot stand. Our societies are already breaking down. We need change.
It’s a shame I started using ChatGPT to summarize such articles:
The author shares concerns about the impact of GPT-4 on jobs, specifically their friend Priya's job as a biomedical data curator. Priya, from a poor background in Uttar Pradesh, India, sends half of her salary home to support her parents. The author tested GPT-4 on a task Priya does daily and found that it could complete the task faster and more cost-effectively. They worry that Priya and others in similar positions could lose their jobs due to the efficiency of advanced AI like GPT-4. The author also fears for their own career in software engineering, questioning the long-term prospects due to AI advancements. They lament the potential negative economic impact of large language models like GPT-4, where a few wealthy individuals may profit while others, like Priya, lose their livelihoods.
