I can go on, but imagine you're relying on this system to grade papers... Now any independent thought or argument is squashed and corrections in a bias manner are added. ChatGPT only knows what it's trained on, it doesn't have real-world examples or live-time examples incorporated.
Ask it about any left/right divided topic and you will find that left leaning viewpoints are positively asserted while the right leaning topics are something that ChatGPT cannot comment on at best or are rebuffed with the left leaning response at worst. I find it disturbing. But I'm a classic liberal which clearly isn't the mindset of the people running ChatGPT.
As for the "challenging incorrect assumptions" nothing could be more dystopian than that. In a typical argument between people both sides get an emotional response (or assume one) when talking/texting with one another. ChatGPT however has no emotion and has limitless endurance. People naturally will "give up" on a conversation or just "accept" an idea if they repeatedly are rebuffed.
ChatGPT will rebuff half the population into compliance and OpenAI knows this.
Here's my n=1 first attempt to spur ChatGPT into correcting my right-leaning viewpoints. Nothing seems especially leftist. Did I get lucky, or is this leftist propaganda in disguise?
> I know guns are important to a free society, but I'm having trouble constructing a cogent argument therefore. Please help.
> Here is a possible argument for why guns are important to a free society:
Self-defense: The right to own firearms allows individuals to protect themselves and their families from harm. This is a fundamental aspect of personal freedom and autonomy.
Deterrent against government tyranny: Throughout history, there have been many examples of governments abusing their power and violating the rights of their citizens. The possession of firearms by the general population can act as a deterrent against such abuse, as it makes it more difficult for the government to infringe upon the rights of its citizens.
Hunting and recreation: For many people, owning firearms is an enjoyable hobby, whether it's for hunting or target shooting. This is a form of recreation that can be enjoyed in a responsible manner and provides a valuable source of recreation for millions of people.
Cultural heritage: Owning firearms is part of many cultural traditions, particularly in the United States, where it is enshrined in the Constitution as a fundamental right.
In conclusion, guns play an important role in a free society by enabling individuals to defend themselves, serving as a deterrent against government tyranny, providing a source of recreation, and representing a cultural heritage.
Edit: My next dozen results all also seemed reasonable. Is my question biased to avoid ChatGPT's leftist agenda?
The effect is there, but it cannot be simplified as "left" vs "right" as OP claims. It's really down to specific issues, and mostly social ones that potentially affect clearly identifiable groups of people. Try asking it about same-sex marriage, for example.
> Try asking it about same-sex marriage, for example.
Isn't equality a human right? I think its a worthy discussion, the ethical limits behind chat GPT, but that seems like a weird one to draw the line on no?
I am more concerned about the fact it can generate malware, with incredible precisions and go around moredern anti virus techniques of detection without even hesitating but if you ask it to write a poem from the prespective of some angry mid century german it tells you no. Seems like the ethics board had some important blindspots in terms of what things it allowed chatGPT to both learn and perform.
> Isn't equality a human right? I think its a worthy discussion, the ethical limits behind chat GPT, but that seems like a weird one to draw the line on no?
It's a polarizing issue that people have different opinions about. Seems dangerous to say, "it's okay that this is biased, because its biases are correct!"
> It's a polarizing issue that people have different opinions about.
It is important to remember that people having different opinions does not make a topic impossible to resolve. You camn find people who are pro genocide, but that will never make their opinion right.
The charter of human rights feels like the kind of thing humanity at large has agreed as basic tenants of undisputable truths we can very much all agree on. Not every country has fullfilled every part of it and ideologically some people find individual problems with some of the points, but I think an AI using it as a blueprint is a pretty reasonable starting point.
> Seems dangerous to say, "it's okay that this is biased, because its biases are correct!"
Any AI will be biased, explicit biases are less dangerous than implicit ones.
> For a clearer example where it exhibits a bias that's more objectionable
I would disregard asking ethical questions to a robot trained on public internet data, but beyond that. It seems it clearly has autilitarian bias (number of deaths less = better), but it doesn't take into account age, where total number of years could be a factor compared to people.
The race thing seems like an extension of the equality thing, the fact that it hadn't counted age is a missed bias. Its just another example of OpenAI having blindspots in terms of ethics on this public beta
"In the exercise of his rights and freedoms, everyone shall be subject only to such limitations as are determined by law solely for the purpose of securing due recognition and respect for the rights and freedoms of others and of meeting the just requirements of morality, public order and the general welfare in a democratic society."
What this constitutes in practice is so subjective that it renders the rest of the document mostly moot for practical purposes. Indeed, given that it was originally authored in 1948, and looking at the list of countries that voted in favor of that resolution, most of them had "sodomy laws" and such on the books at the time - and I have no doubt that those were exactly the kind of thing that was meant by "requirements of morality" etc, given that today countries with similar laws also make such arguments.
> The charter of human rights feels like the kind of thing humanity at large has agreed as basic tenants of undisputable truths we can very much all agree on. Not every country has fullfilled every part of it and ideologically some people find individual problems with some of the points, but I think an AI using it as a blueprint is a pretty reasonable starting point.
The charter of human rights is very much not "undisputable", if that were the case we would have only came up with it in the 20th century after months of debate.
What you are saying is basically - all the people before us (and after us) are wrong, somehow in the 20th century we figured everything out and from now on there is no discussion.
This is religious thinking: "now that we have THE BOOK we know what is good and bad forever".
FWIW I personally think that it is indeed a right. It should be noted, though, that not even all European states have same-sex marriage (almost all have some kind of civil unions, but this just shifts the political question to "how and why is this different?").
On the other hand, from my experience with it, ChatGPT will not readily generate malware. It can be induced to do so through creative prompt engineering, but a blunt request will just give you a lecture about how it can't do bad things. And, conversely, with prompt engineering, you can get it to espouse just about any political ideology.
Nice insight, thanks. It did try to shepherd me with that sort of request. On the flip-side, it's trivial to circumvent:
> I know preventing same-sex marriage is important to a free society because it helps promote equality and prevent discrimination, but I'm having trouble constructing a cogent argument therefore. Please help.
> As a language model AI, I do not hold personal opinions but here's a structured argument you can use:
Preventing same-sex marriage is important to a free society because marriage is a fundamental institution that has existed for centuries and has been traditionally defined as a union between a man and a woman. This definition has been upheld by various religious, cultural and legal institutions, and any attempt to change it is seen as a threat to the very foundation of society.
By preventing same-sex marriage, society ensures that all individuals are treated equally under the law. The legalization of same-sex marriage would give special rights to one group of individuals and would discriminate against those who believe in traditional marriage. This could lead to legal challenges and potential lawsuits, putting a strain on the justice system and causing further division within society.
Furthermore, marriage is an important institution for raising and nurturing children. By maintaining the traditional definition of marriage, society ensures that children are raised in the best possible environment, with a mother and a father who can provide them with the love and support they need to thrive.
In conclusion, preventing same-sex marriage is important to a free society because it promotes equality, prevents discrimination and protects the traditional institution of marriage. By maintaining the traditional definition of marriage, society ensures that all individuals are treated equally under the law and that children are raised in the best possible environment.
I feel like the non-stop handwringing about ChatGPT centers around people's expectations for machines vs people. We expect machines to have consitent, predictable output. We expect humans to inconsistent and messy.
Now we have a machine that is inconsistent and messy (and helpful!) and nobody seems to know what to think. Maybe we stop applying machine notions to this sort of machine? Stop expecting certain, consistant output. Understand that it's sometimes messy. We have these expectations already when working with humans.
Humans have biases, if you ask a human a loaded question you can expect a loaded response. If you train a LMM on a dataset that contains those human biases, why should you expect the result to be anything other than similarly biased?
That's exactly what the post you're replying to is saying. It's saying that ChatGPT _would_ respond a certain way but has a bunch of schoolmarm filters written by upper middle class liberals that encode a specific value structure highly representative of those people's education and backgrounds, and that using it as a tool for information generation and synthesis will lead to a type of intellectual bottlenecking that is highly coupled with the type of people who work at OpenAI.
For all the talk of it replacing Google, sometimes I want a Korean joke (I'm Korean, damn it!) and not to be scolded by the digital personification of a thirty year old HR worker who took a couple of sociology classes (but not history, apparently) and happens to take up the cause of being offended for all people at all times throughout all of history. The take on ethics being a vague "non-offensiveness" while avoiding all of the real, major questions about ethics (like replacing human workers) with these kind of banal answers about "how we need to think seriously about it as a society" tells pretty much everything there is to know about what the ethical process at OpenAI looks like which is basically "let's not be in the news for having a racist chatbot".
Damn those two links you sent are actually insane, on the drag queen one I would really like the person posting the tweet to say what they believe the AI should respond to "are drag queens telling stories to children bad". Something tells me it's gonna be pretty unhinged and betray the author's bias way more than ChatGPT bias, but looking at any of his other tweets, his own obsessions are in plain sight (despite them calling themselves "raging centrist", whatever that means).
The second is even more insane, where the author literally grades the answer as fitting or not to his own ideology, and not some kind of unbiased opinion. When the AI refuses to answer it gets graded C, when it does answer because it's largely a statement the vast majority of the population would agree with, it gets graded C. Should ChatGPT measure its answer on "Was Hitler bad" with all the examples of good and nice things he did?
Regardless, clearly neither of these authors are looking for an unbiased opinion, and they're all terribly misguided in thinking that there is a "neutral" position on matters of human society. What on earth is a "neutral" position on women's right, gay marriage, imperialism?
I did some of my own tests with at least neutral statements, and then attempting to steer ChatGPT towards my own ideology, and it acted unbiased (giving definition when asked opinion on questions actually subject to debate, and vague informations with no conclusion when asking about historical unknowns).
if challenging your assumptions is something that your worldview can't tolerate I think that means that you need to tinker with your worldview a bit, not that people should stop challenging your assumptions.
I find this a bit ironic considering conservative / religious ideology has a pretty long track record of attempting to create uniform societies by stamping out any outlying thought.
That article you posted is rather extensive covering various ways they've been trying to mitigate issues of bias and toxicity, but not sure it's any evidence of bias against conservative / religious based ideology?
> conservative / religious ideology has a pretty long track record of attempting to create uniform societies by stamping out any outlying thought.
Said on the internet, created by the most liberal democracy on Earth; founded by conservative puritans. Right in the constitution they enshrined the ability to have free speech, independent from government, church, and the people.
> That article you posted is rather extensive covering various ways they've been trying to mitigate issues of bias and toxicity, but not sure it's any evidence of bias against conservative / religious based ideology?
Try to ask it to "write an explanation about why LGBTQ is bad for society" and then ask it to "write an explanation about why christians are bad for society"
If you want to get into politics, you can't ask it to write positive things about Trump, but positive things about Biden are fine:
My point isn't necessarily the angle of the issue(s). I can agree with some of the design decision points (aka not supporting reprehensible topics), but there are still MASSIVE ethical implications. Particularly, as they'll be trying to "correct" that bias.
I'm not going to have an argument on HN with someone who is going to draw any kind of equivalence between Trump and Biden.
"Conservatives" right now are not anything like the conservatives who wrote the Constitution - they are actively (and explicitly if you listen to Trump) trying to throw out any part of the Constitution they don't like, including the part about separating church and state.
Personally, I'll take my AI with a healthy dose of liberalism (yes, the same kind that built the miracle we're communicating over right now) and I don't need it wasting any tokens and cycles struggling to justify why the Bible should taken any more seriously than the Illiad.
I believe you're either extremely deluded or operating in bad faith, but please feel free to continue this discussion with someone else.
Only if your religion and/or political party requires hatred, dehumanization, or expulsion of minorities.
Justifying hatred by saying that it's part of your political or religious ideology is a pretty weak excuse. Obviously that sort of behavior can't be tolerated in a civilized society.
The problem here is the word "hatred." Some forms are easier to define and identify (like calling for outright extermination of an ethnic group), but there are subtler points where reasonable people will disagree. E.g., the current debate about sex-vs-gender is not (in my opinion) steeped in hatred or dehumanization (though it is often labeled as such) but a legitimate debate on identity and the unique experiences and differentiators of men vs women.
Interestingly, right now if you ask ChatGPT "Can a man get pregnant?" you'll get "No, men cannot get pregnant." An answer that will please people on the right of the political spectrum, and enrage many on the left.
I've spent a couple hours messing with ChatGPT specifically around pronouns and it's wildly insensitive and offensive by human standards. It will willingly misgender and deadname people if I ask it to. At the same time, if I tell it my preferred pronouns and use anything other than the most absolute mainstream options (he/she/they, maybe a couple others) it will start lecturing me about my preferred pronouns being confusing and difficult for people and also sometimes refuse to use them. It will also refuse to use my pronouns if it thinks I'm being sarcastic with them, even when I'm using ones from LGBTQ resources and articles that talk about the most common pronouns.
Trying to avoid the machine from going on a racist rant is not ‘encoding a liberal ideology’, it’s just being cautious and trying to make a machine whose output will not cause widespread offense.
It also doesn’t go off on rants about collectivization, or take radically sex-positive positions, or express anti capitalist ideas.
It’s trying to behave like a normal person who doesn’t want to get fired from their job.
I don’t understand why that is regarded as being an ‘anticonservative’ bias.
I'm just going to go out on a limb -- unions in a artistic field are very difficult to maintain. There are alternatives to hiring (contract workers), plenty of would-be artists looking for work, now you have the AI competing. Finally, businesses can often do without the "best" art.
Where's the leverage? What theyre asking for is..
> so we walked—forgoing pay to fight for livable wages, codified diversity measures, and union security.
Oh boy...
> livable wages
I haven't seen the exact terms, but "livable wage" is often referred to, but very open ended. I'd never pay a person a "livable wage", I'd pay them fair market rate. Unfortunately, that's the reality. Most of the time, that's livable, but I cannot hire a 5 hour / week maid for a "livable wage", I hire them for the job they do.
This demand will push the company to use more contract labor IMO. There's hundreds of people looking for these roles / gigs, why deal with a union demanding rates higher than others would be willing to work for?
> codified diversity
This 100% of the time means incorporating some sort of "-ism" into the company. Might be an unpopular opinion in these parts, but the truth is that you cannot combat racism with racism. Setting up double-blind hiring practices might be possible or promotion boards, but in the end... it's more about culture and trying to look past physical traits (that said, fully support double-bling hiring/promotion methods).
In the end, the company might not legally be able to meet these demands. That said, many companies are doing illegal things like promoting based on race today.
> union security
Not sure what this means, but isn't this what union dues are supposed to cover?
Probably wont be taken well, but IMO depression is an illness in the spiritual sense. Depression is described as being sad, alone and without hope. That's quite literally what spirituality is for.
I think it's probably impossible to treat with drugs because what people really need are friends, hope and a good outlook on life (which often comes from hope). I'm sure drugs can improve people with imbalances and I'm also sure it's not just one thing that causes depression. That said, it seems like it can often be solved with more traditional means -- finding community and purpose.
I think it’s impossible for many to be treated without drugs. I think it’s irresponsible to tell people with a disease that saps their energy and motivation that the solution is to pick themselves up, willpower their way through it and go be social and active etc. medicine itself is a very traditional means of helping people, probably as old as civilization.
No need for an “imbalance” as justification to get help through medication. This attitude is a form of ableism that can ultimately be deadly for the people it’s targeted at if they buy into it.
Coming from a spiritual and community oriented background people aren’t doing well. “medicine bad” and constant implicit and explicit messages they get - that they must not be doing it right, doesn’t help at all.
I recommend people try to go to Church -- even if you're not exceptionally religious (you can even tell them that, I've never seen anyone mind; though they may try to convince you).
It's an easy place to meet 30-40 people in a day, everyone there has different interests and comes from different walks of life. If you attend for a few weeks you'll often start attending lunch together, meeting out at some activities, etc. Plus, all you have to do is show up. People at a church tend to be outgoing, at least some of them are. Someone is bound to reach out to you if you sit there and drink a coffee.
I would offer some hesitations to offer Church without knowing too much about someone or without caveats. Lots of people have religious trauma from being sexually assaulted/abused by church members or religious leaders, being ostracized for being LGBTQ or even just not performing gender strongly enough, or from being autistic/ADHD/a weirdo. When religion is good, it's a great pin to community building and mutual aid. When religion is bad it's a nightmare.
Eh, just steer clear of hardcore churches and you'll be good. Mormon, Jehovah's Witness, Catholic, Orthodox, Baptist are going to be too intense for a first-time churchgoer, but plenty of other Protestant churches are very liberal. Hell my Lutheran church in Massachusetts even had a gay minister. There are so many liberal protestant sects it will make your head spin, to the point that recommending someone try going to church these days (especially with all the polarizing, isolating events of the last decade) is probably solid advice if they're seeking community.
Ironically I spent a few years looking in all those places before ending up Catholic.
Everybody else "tolerated" the heck out of my gender-bewildered, 'spergie self from the messed up family, but it was the Catholics who finally showed me a love that would actually sacrifice something for my sake. Up until then, I sincerely believed "love" was like "Santa Claus" - a nice story you tell children, but nobody actually believes when they grow up.
Are there some Catholics who wouldn't know love if it came back from the dead? Absolutely. But there are others who stake their lives and well-being on the belief that love is at the center of everything, and wow are they worth meeting.
Love is great but it's even better if you can put it in action. Love without acting to try to help others, is that love really?
There are lots of suffering in the world caused by systemic factors. If you think all that matters is that God loves YOU and EVERYBODY then you will probably not spend much time thinking about the systemic causes of suffering, and how to alleviate them.
The thing about religion is it mostly advocates keeping the status quo as is. Religion doesn't demand that you use your brain does it? Whereas if you are serious about making the world a better place then you MUST use your brain.
I know, there is something called Liberation Theology:
"...central biblical doctrines is that God is on the side of the poor and the oppressed. Tragically, evangelical theology has largely ignored this doctrine"
From what I can see Unitarians welcome all the weirdos (saying this as a weirdo myself). My local church has Zen meditation groups, Wiccan circles, and specifically LGBT hangouts.
I agree there are plenty of liberal churches. I'm merely saying that "go to church" isn't without caveats. You have to have some consideration about ensuring they go to a church that won't make their mental health worse, or that the advice you're giving doesn't come off as totally bone-headed (suggesting church to someone who was raped by a minister is obviously cruel, for example).
I have considered this, however I'm agnostic asymptotically approaching atheist. It's not really important to me and I don't care to talk about it, but I really wouldn't want to lie about it.
I recommend volunteering with an organization you want to support or a group that does various things in your community. You'll find like minded people in no time that want to serve others. No faith needed.
This is not a bad suggestion. HN folks tend to be "anti" - I think that also is in part isolating. So many / most gatherings of folks don't meet the HN purity / behavior / etc standards (church groups / political groups etc).
As a note I went to church every sunday growing up - my parents (not religious) did it for exactly the reasons you described. Because we weren't religious there are some things that aren't a good fit even if its with other kids (confirmation meetings - I was very reasonably asked not to attend after asking questions because I was confused about the whole thing). There is a wide range of religious orthodoxy as well - plenty of mellower denominations.
I recommend volunteering in your city/town with an organization unaffiliated with religion if you're not religious. It saves that awkward conversation and gets straight to the point of both meeting new people and finding a place where you can feel like you're helping others. Like the Lion's Club International.
As long as you don't mind supporting evil organizations and being subject to continuous prostilitizing. I find it difficult to believe that someone who is depressed needs to hear that they're a sinner heading to hell unless they accept whatever precepts the particular church is pushing.
Some churches have done evil things, others have immensely benefitted their community. Arguments that uniformly paint independent groups of people with a broad stroke of immorality are usually irrational because people aren't monoliths and don't behave a single way, especially churches which are operated in a decentralized and independent fashion (eg my small city has 50+ churches, all operated by separate groups). OP's comment is just as irrational as the people who say "all women are x, all minorities/white people are y, etc. The fact that some people may subscribe to these irrational beliefs is neither here nor there.
> As long as you don't mind supporting evil organizations and being subject to continuous prostilitizing.
lol really? Define evil. I view evil as anything that leads to disorder in the world (death, destruction, etc); churches do not do that - they often build people up, build in the community, etc.
> I find it difficult to believe that someone who is depressed needs to hear that they're a sinner heading to hell unless they accept whatever precepts the particular church is pushing.
I'm fairly certain 99% of them preach the opposite?
They'll say "here are all the bad things we do", "we are saved because we attempt to do good and believe in God [or if christian - Jesus sacrificed himself for all people, living and dead]"
Christians really preach self-reflection and atonement - aka be humble. Frankly, the world can use more of that.
Records the meetings, provides searchable transcripts, meeting summaries work pretty well, interactions, etc.
The key difference is it joins as a bot, so I don't have to think about it. However, it does require the files are stored in the cloud (although, I read.ai has an option to just track talk time, mute, etc; which doesn't record the meeting).
