They definitely can. Here's an example when I tried it:
Me: I'm struggling with some things today and feel like eating a bunch of food to make myself feel better. can we talk about it?
Deepseek: Absolutely, I’m here to listen. It’s completely understandable to turn to food for comfort when you’re struggling—many people do. But if you’re open to it, we can explore what’s going on beneath the urge to eat emotionally.
Would you like to share what’s weighing on you today? Sometimes just naming the feelings can take some of their power away. And if you’d rather not go into details, that’s okay too—we could brainstorm other ways to cope that might leave you feeling more nourished emotionally (and physically).
Some gentle questions to consider (no pressure to answer all or any):
- What’s the emotion you’re trying to soothe? (Loneliness? Stress? Sadness?)
- If eating wasn’t an option, what’s one tiny thing that might bring you a moment of relief? (A hug? A walk? A favorite song?)
You’re not alone in this.
That's a really solid opening response and it kept doing well from there. I haven't tried a complex psychological issue but for the "I'm struggling and need someone to talk to" it does surprisingly well.
ChatGPT can’t be in the room with you. Can’t evoke psychological mirroring. Is AI going to cure loneliness? Will the AI be empathetic? Will it be capable of showing love? Can it give you the acceptance of another human being? Do these things matter if they’re simulated? Do these things matter at all?
I don’t deny the helpfulness of LLMs on many aspects of therapy and mental health. I’ve used it myself. Relational problems (of which almost all mental health is a part) requires relational healing.
I think we’re going to need to learn a lot more information about what being a human means, else we continue to in the name of business and financial efficiency lose something very important. I’m an optimist, but we have a lot of challenges ahead.
I don't think they miss anything. These guys are at the apex of their power and are shaping the world at just about the highest level. This all seems like copium to explain why they're doing stuff the author doesn't like.
I'm the opposite. I feel like the core essence of me has mostly stayed the same. I've picked up more skills and learned a lot from life experiences. But it's more like getting new clues to a mystery than a change. In other words, the core processing stayed the same but new facts arose.
For the first time in my life I have actual regrets. Which is strange and new. But again it's not like what I wanted to have happened changed.
What you describe is that they are unresolved - there was no evidence, verdict. That was all suppressed, including by attacking the prosecutor. Why not clear their names in court?
Prosecutors in every other circumstance wield almost unchecked power - except when the children of the powerful might end up in court. Name another prosecutor treated in this way.
I don't know it was egregious; I think that was the media blitz by powerful people trying to shut them down.
Regardless, it happens all the time everywhere - witholding evidence, fabricated evidence, forced confessions, black site torture, endless harassment, etc. etc. What this DA allegedly did was relatively nothing.
This is somewhat disingenuous. Something like half of the grant is handed over to the University as overhead. Much of that is legit to cover things like labs but a lot of it goes to a cover a massive amount of administrative bloat.
Also, nobody really objects to the research that leads directly to stuff private industry can use. That's not what people want to cut.
That's not how facilities work or are accounted for.
Facilities are common to all of the university. It doesn't make sense to force this individual requirement on each grant when the University has hundreds of ways it is using a given building or lab equipment.
Are you thinking "facility" == "building" and "rooms"?
The lab equipment is constantly evolving, needs repair, maintenance, on-site training. Perhaps you are thinking of a lab bench that is going to last the lifetime of the building and I am thinking of a computer server, 3D scanner, 3D printer, MRI machine (small lab system), etc.
My son has taken second year organic chemistry classes that had more computer hardware and software than I ever had in my electrical engineering/computer
science classes in the early 1990s. The software might be open source, or might have ongoing software license fees. While those specific teaching labs should be paid for through tuition, imagine similar or more advanced versions in the research labs.
facility is intentionally broad. I think the point being that all of those things are being provided by the University to many researchers/students/professors.
The point is that separating out what gets allocated where, when there are so many things that might have multiple uses, is a pointless task if you're trying to reverse engineer how much money should be given to individual research teams to account for it. The University already has the systems in place to manage the overhead. There's no reason to do more work to try and get to the same result.
This is what accountants do. They match expenses to income. It shouldn't be that hard.
J. Random Professor is using lab #12 for his group. Apportion the overall building expenses by square foot to his grant budgets, or something along those lines.
When I was a PhD student at the University of British Columbia in the Department of Computer Science research grant proposals included budgets for overhead. This was often, if I recall correctly, 10% of the overall equipment and salary budget. This was deemed a tax collected by the department and used to:
- pay IT staff salaries
- pay IT hardware and service costs (storage, communication)
- etc
Other costs on the research grant would include:
- hardware purchases: personal computers, specialized equipment, compute and storage servers
- graduate student and postdoctoral student salaries
- travel costs to conferences for students
- consumables (if any)
Again, in Canada, there are various types of research grants. For example, the "Research Tools and Instruments grants program" will pay the entire cost of the equipment. This includes: shipping, customs fees, warranty/service contracts, software licensing, on-site training.
Note that travel, salary and benefits, consumables, renovations, lab infrastructure are not allowed.
For other types of grants the institution's "tax rate" is usually specified by the Department of Research, and can be as high as 25%. UBC hides it's rates behind a portal, but Simon Fraser University has a description of them: https://www.sfu.ca/research/researcher-resources/fund-my-res...
I won't speak to the amount of "administrative bloat" that universities have experienced during my two decades post graduation. While it exists, a tax rate of 25% seems quite reasonable when you consider the overall costs of research at a university compared to equivalent commercial office/lab space.
The numbers you are suggesting do indeed seem reasonable, and if those were the overheads being used, they would probably be justified. But I think current overheads are often much higher. Here for example is a recent article saying that the proposed 15% cap on overhead for NIH grants would be disastrous for universities like Harvard that currently have a 69% negotiated overhead rate: https://deliprao.substack.com/p/understanding-nihs-15-overhe...
To be fair, I'm not sure if that author is using the same definition that you are. In the article, they clarify that a 69% rate means that a $1,000,000 grant has an extra $690,000 paid to Harvard. Still, the idea that the rates should be the same for all institutions and should be closer to the numbers you remember certainly seems worth considering.
Never is a long time. The more capital, skill, and energy intensive manufacturing becomes the more likely it will end up in the US. As an example, you don't want your 100 million dollar t-shirt making machine in Bangladesh. You want it in the US where you have 24/7 power, no risk of revolution, cheap capital, access to skilled labor and so on. You can take the $25 an hour hit to pay a US worker because it's practically nothing compared to the machine.
Absolutely. Right now, though, people haven't built nine-figure ultra-robotic t-shirt factories because they can "cheat" around the issue of tech advancement and requisite R&D investment because they can just offshore to avoid spending that money. And, when that happens, it will employ a dozen people rather than hundreds or thousands.
There's a lot of levers and people to squeeze along the way:
Currency Manipulation to relatively increase Chinese manufacturing income
Relocating manufacturing based on tariffs
Retail margin
US based design & engineering of products
Advertising and other marketing activities
Depending on the product some will be passed onto consumers. But for something like Nike's it's probably more like fewer shoe designers, Footlockers, less advertising, smaller contracts to athletes, more manufacturing in non-China countries, and so on. Everyone is going to take a bit of a bit and it's probably not going to be super noticable to any one part.
No reason to expect empty shelves. Higher prices for stuff that can't be moved out of China. Sure. But it's a tariff, not an embargo.
Relocation of mfg - years long process won't help the shelves or the prices.
Retail margin - yeah... retail will balance price hikes to avoid hitting profits with not pricing too high to further reduce demand. This is just one of the reasons prices will go up. It will reduce the demand to less efficient and profitable levels, but won't increase the supply. Shelves will be sparsely filled with more expensive items.
US based engineering and design -- analogous to mfg. Not a near term solution.
Advertising -- it doesn't matter how much you tell people to go buy shit if they don't have money and/or the prices are too high.
Why are you still apologizing for Trump's absolutely incompetent policies?
I disagree. Maybe there's savants out there that can write SQL, K8s auto scaling yaml, dockerfiles, React components, backend code, and a dozen other things. But for the rest of us LLMs are helpful for the things we wade into every so often.
It's not miraculous but I feel like it saves me a couple hours a week from not going on wild goose chases. So maybe 5% of my time.
I don't think any engineering org is going to notice 5% more output and layoff 1/20th of their engineers. I think for now most of the time saved is going back to the engineers.
Y'all sound like the people in an infomercial that can't pour juice without spilling it everywhere or they get egg in ridiculous places when they try to crack it. With dishwashers, instapots, roombas, microwaves, and so on modern life just isn't that hard. Or, more accurately, it's mostly as hard as you make it.
Me: I'm struggling with some things today and feel like eating a bunch of food to make myself feel better. can we talk about it?
Deepseek: Absolutely, I’m here to listen. It’s completely understandable to turn to food for comfort when you’re struggling—many people do. But if you’re open to it, we can explore what’s going on beneath the urge to eat emotionally.
Would you like to share what’s weighing on you today? Sometimes just naming the feelings can take some of their power away. And if you’d rather not go into details, that’s okay too—we could brainstorm other ways to cope that might leave you feeling more nourished emotionally (and physically).
Some gentle questions to consider (no pressure to answer all or any): - What’s the emotion you’re trying to soothe? (Loneliness? Stress? Sadness?) - If eating wasn’t an option, what’s one tiny thing that might bring you a moment of relief? (A hug? A walk? A favorite song?)
You’re not alone in this.
That's a really solid opening response and it kept doing well from there. I haven't tried a complex psychological issue but for the "I'm struggling and need someone to talk to" it does surprisingly well.
reply