What would the pain-points be, in your view? Is it that the LLM is generally not “intelligent” enough, or is there some other limitations? As someone who enjoys using LLMs for self-education up to the bachelor level, I’m curious where doctorates might face issues.
From my experience using LLMs and supervising PhD students, the LLM is too focused on solving a task rather than educating or opening paths. It’s great if you have a specific question to ask, even at quite high level, it can explain you group theory or quantum chemistry quite well if you ask the right questions. The problem is that if students knew the right questions they would not be students. LLMs can get stuck explaining a topic without realising that it would be useful or interesting to branch out to something else. They can give you all the pros and cons of a given simulation technique without even trying to tell which of those actually matter in a specific case. They tell you if you ask, but you have to know what to ask.
LLMs are not great at open-ended discussions and don’t benefit of experience in the same way humans do. They are better to solve problems than to explore ideas. They keep getting better, though.
How are you using for self-ed? Would you please link to something you have found useful? Any time I've tried to do something basic like use an included learn skill/style or roll my own variant, it doesn't click, and I end up just doing what I would have done 10 years ago: watching lectures, reading the book, etc.
I tried to do a project on Claude.ai to self-learn cs 15-213, gave it a skill, pointed at the cmu site, put the labs and my notes up on GitHub, but ended up just reading the book, doing problems, and asking questions as needed. I struggle to engage in long-form work in this manner, because the bot is always pestering me about the course itself. I could probably just write "don't ask me about coursework" and that would fix it. Poor Claude always wraps an answer to my one-off question with "would you like me to add this to the week x materials?"
I find the cost of my writing the question, waiting for the reply, parsing the llm response and translating it to something that makes sense, understanding it, and cross-referencing, is too high. I suspect I'm holding it wrong.
Your PhD advisor would be lending their wisdom and intuition to get you pointed down a promising (novel) research path. I don't think LLMs have been demonstrated to be at human level for that.
wasn’t there, a year or so ago, some sorta OpenAI plan where you’d pay $400 or something and get “PhD-level research“ capabilities? I wonder what happens to that :)
Let's not forget that we're talking about people getting hurt, that's the core topic here, yes? The most reasonable immediate cause for the people getting hurt is that there was too much chlorine in the water. Because the dosing system pumped too much chlorine AND the monitoring system failed to alert. Because it was set up to only use email AND the email failed. Because someone deployed a wrong config on MS's cloud infra. And so on.
Not one but two of the hotel's systems failed to operate properly. The chlorine pumping system pumped too much chlorine and the last resort alarm failed to alert.
As I said, there's plenty of blame to go around as a matter of general principle. But for what happened here the hotel bears the responsibility towards their guests, not the pumping or monitoring system developers, not Microsoft. The only reason MS in the title is because that failure is big news these days.
On a technical note, even if they had a backup email provider they'd still be screwed because the people getting the alert were probably employees on the single provider (back to SPOF). SMS could have been a good parallel option. Ideally also some physical control panel that triggers an alarm when any safety critical condition occurs. On the chlorine pumping system, that shouldn't be a dumb preprogrammed pump, it should come with it's own sensors and detection loop independent of any external system, something that proactively stops it before it breaches the safety limits.
That was the original concept for the booster. You need some sort of giant rocket manipulator at the launch pad no matter what. If you can make it double as an active landing target, you go from needing cm level to m level landing precision.
See the repeated prisoner's dilemma, where the fact that you keep repeating the game completely changes what it means to have an optimal strategy. A company doesn't make a choice to collude or not once, they make it over and over again.
As I said another comment, this all just feels like everyone inadvertently saying “only the most dedicated should be given direct access to these tools.” I wouldn’t be necessarily against that if the alternative wasn’t yet another privacy-violating subscription minefield dominating 99% of the landscape. That’s what that road leads to. Barriers -> Less participation -> less created outside the prescribed corporate play pen -> more people in the play pen.
It would be harder for a short period of time. Then it will be made easy again. As a baseline, it's not going to get harder than pirating a movie unless it's made criminal.
Please don’t get hung up on my word choice. The point is this: I don’t understand why you think that it’s a given that adoption would occur at a meaningful level. We have it right now. Why would we give that up for the promise that we’ll get to again? It makes no sense. We should not want access to be eroded over time and then cope with “well we’ll get an alternative.” That’s not a given!
It’s not going to stop with hugging face just like ID requirements aren’t stopping at pornography. It is much harder to regain these things once they are lost.
No, I am saying if something was as centralized and as easily accessible without VPN and torrenting software like Napster, we would have far more people able to do it today than we already do. Frankly if it was that trivial still the music industry would probably be buckling unless they changed things drastically.
A better example to illustrate my point and distinguish my actual stance from what you’re saying would be if the Pirate Bay went down today or suddenly became far more difficult to access, such as legislation passing in major nations making it illegal and reasonably enforceable on the individual level for having the media/browsing TPB. If everybody had to go to private trackers and communities there would be a severe drop in participation, and a subsequent severe drop in available media for pirating as seeders would drop in number.
TPB is a very critical central repository for most people pirating, just like hugging face is for abliterated/uncensored models. If you make it more difficult to access these things, fewer people will access them. This is not controversial in the slightest.
No, your comparison with TPB being banned is not adequate, it is one thing for a private entity to decide to censor something and an entirely different thing for a state to start enforcing a ban on free file sharing. To be fair some have tried and in some countries you need to take extra precautions but still, private entity censoring vs state censoring is a whole different thing.
The music / tv show industry / gaming industry did not buckle because people are willing to pay for convenience but they still lost revenue. Gabe Newell's wisdom has come true, make a game affordable and easy to buy and people will buy rather than pirate. Same goes for music, streaming is cheap enough that I don't care to pirate music.
I do pirate TV shows because they're not all in the same place and the picture quality streaming services offer is bad. And pirating has never been hard for anyone with even a little bit of computer knowledge.
And I still don't get what your solution is, hugginface has the right to do whatever they want in a free market. If you made it an utility then the state might decide to censor it. The only real solution is torrenting.
> Even if you only include OpenAI and Anthropic, they would probably buy every single GPU, TPU, and XPU that TSMC, Samsung, and Intel could produce if they had sufficient money
The trouble that that idea is that there comes a point where the generated AI needs machines to test the code that is generated... and it actually puts a limit on the growth of AI.
reply