Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OpenAI, Google and Anthropic are struggling to build more advanced AI

bloomberg.com

Post reply on HN
Print view View original

581–590 of 622 posts

Re: OpenAI, Google and Anthropic are struggling to build more advanced AI

#581

Post by Vampiero »

alainx277 wrote: post #565
Vampiero wrote: post #528

Earlier quoted context omitted.

Here is an example of a task that I do not believe this generation of LLMs can ever do but that is possible for an average human: designing a functional trivia app. There, you don't need to invoke Turing or compiler bootstrapping. You just need one example of a use case where the accuracy of responses is mission critical

o1-preview managed to complete this in one attempt: https://chatgpt.com/share/67373737-04a8-800d-bc57-de74a415e2... I think the parent comment's challenge is more appropriate.

Have you personally verified that the answers are not hallucinations and that they are indeed factually true?

Oh, you just asked it to make a trivia app that feeds on JSON. Cute, but that's not what I meant. The web is full of tutorials for basic stuff like that.

To be clear I meant that LLMs can't write trivia questions and answers, thus proving that they can't produce trustworthy outputs.

And a trivia app is a toy (one might even say... a trivial example), but it's a useful demonstration of why you wouldn't put an LLM into a system on which lives depend on, let alone invest billions on it.

If you don't trust my words just go back to fiddling with your models and ask them to write a trivia quiz about a topic that you know very well. Like a TV show.

Re: OpenAI, Google and Anthropic are struggling to build more advanced AI

#582

Post by tim333 »

lcnPylGDnU4H9OF wrote: post #183
demosthanos wrote: post #135

Earlier quoted context omitted.

> that does not mean that there arn't giant shocking leaps forward coming from slightly different directions. Nor does it mean that there are! We've gotten into this habit of assuming that we're owed giant shocking leaps forward every year or so, and this wave of AI startups raised money accordingly, but that's never how any innovation has worked. We've always followed the same pattern: there's a breakthrough which c…

> Altman has been telegraphing that he's eyeing the exit Can you think of any specific examples? Not trying to express disbelief, just curious given that this is obviously not what he's intending to communicate so it would be interesting to examine what seemed to communicate it.

Yeah, listening to him last week he seemed very unlike that https://www.youtube.com/watch?v=xXCBz_8hM9w&t=2324s

Re: OpenAI, Google and Anthropic are struggling to build more advanced AI

#583

Post by danielbln »

namaria wrote: post #536
danielbln wrote: post #511

Earlier quoted context omitted.

We built planes, which works quite differently from birds, in the span of what, 100 years? I think we've long left evolution behind when building machines, thinking or otherwise, so I'm not sure why the powerful but inefficient evolutionary process is held to some gold standard here.

It's not a gold standard. It just shows how difficult the problem really is. Flying machines rest on the excess power of internal combustion. They have nothing to do with bird evolution.

The fact that it has nothing to do with evolution is exactly my point. We built something that can fly but has nothing to do with how birds fly. So we might be able to build an AGI that isn't based on biological mechanism and/or evolutionary principles.

Re: OpenAI, Google and Anthropic are struggling to build more advanced AI

#584

Post by ikrenji »

JohnMakin wrote: post #256
jmward01 wrote: post #175

Every negative headline I see about AI hitting a wall or being over-hyped makes me think of the early 2000's with that new thing the 'internet' (yes, I know the internet is a lot older than that). There is little doubt in my mind that ten years from now nearly every aspect of life will be deeply connected to AI just like the internet took over everything in the late 90's and early 2000's and is now deeply connected t…

It's strange to me that's your takeaway. The reason that the internet was overhyped in the 2000's is because it was and also heavily overvalued. It took a massive correction and seriously disruptive bubble burst to break the delusion and move on to something more sustainable.

you do realize all of the worlds most valuable companies are either built on/for internet or heavily leverage it

Re: OpenAI, Google and Anthropic are struggling to build more advanced AI

#585

Post by vidarh »

tim333 wrote: post #577
vidarh wrote: post #555

Earlier quoted context omitted.

Yikes, that was an unfortunate auto-correct and too late to edit. "LLM losers" was meant to be "LLM users".

I thought you were maybe a bit rude there!

Yeah, not my intent. I use LLMs a lot myself too...

Re: OpenAI, Google and Anthropic are struggling to build more advanced AI

#586

Post by tim333 »

zkry wrote: post #559
jmward01 wrote: post #175

Every negative headline I see about AI hitting a wall or being over-hyped makes me think of the early 2000's with that new thing the 'internet' (yes, I know the internet is a lot older than that). There is little doubt in my mind that ten years from now nearly every aspect of life will be deeply connected to AI just like the internet took over everything in the late 90's and early 2000's and is now deeply connected t…

There are a lot of comparisons that could be drawn: web 3.0, the internet, the dot com bubble, etc. but I think the most appropriate comparison would be to... AI in the past. No one doubts that there was a lot of value coming from that research. In fact a lot of it is incorperated in our every day life. But it didn't live up to its hype. I suspect the same will be true for this wave of AI (and perhaps an associated A…

My recollection of AI in the past is that it was nothing like this.

If you look at the Wikipedia article 'History of artificial intelligence' for now it has 'AI boom' and '2004 Nobel Prizes' but everything earlier is kind of meh.

I remember sitting down with pen and paper to try to write a ChatGPT type chatbot 44 years ago and of course totally failing to get anywhere, but I've followed the goings on since and this is the first time this stuff is working well.

Re: OpenAI, Google and Anthropic are struggling to build more advanced AI

#588

Post by slashdave »

eli_gottlieb wrote: post #117
iandanforth wrote: post #47

A few important things to remember here: The best engineering minds have been focused on scaling transformer pre and post training for the last three years because they had good reason to believe it would work, and it has up until now. Progress has been measured against benchmarks which are / were largely solvable with scale. There is another emerging paradigm which is still small(er) scale but showing remarkable res…

>The best engineering minds have been focused on scaling transformer pre and post training for the last three years The best minds don't follow the herd.

I hear what you are saying, but "innovation" is also often used to excuse some rather badly engineered concepts

Re: OpenAI, Google and Anthropic are struggling to build more advanced AI

#589

Post by slashdave »

mvdtnz wrote: post #354
iandanforth wrote: post #47

A few important things to remember here: The best engineering minds have been focused on scaling transformer pre and post training for the last three years because they had good reason to believe it would work, and it has up until now. Progress has been measured against benchmarks which are / were largely solvable with scale. There is another emerging paradigm which is still small(er) scale but showing remarkable res…

> The best engineering minds have been focused on scaling transformer pre and post training for the last three years because they had good reason to believe it would work, and it has up until now. Or because the people running companies who have fooled investors into believing it will work can afford to pay said engineers life-changing amounts of money.

The improvements in transformer implementation (e.g. "Flash Attention") have saved gobs of money on training and inference, I am guessing most likely more than the salary of those researchers.

Re: OpenAI, Google and Anthropic are struggling to build more advanced AI

#590

Post by tim333 »

nikkwong wrote: post #452

Didn’t Sam Altman just go on some podcast last week and tell the world that he thought “We know exactly what to do to be able to reach AGI now”. What’s going on, is he just posturing?

Yeah this https://www.youtube.com/watch?v=xXCBz_8hM9w&t=2324s

Not quite that wording. More we know which way to head. I think he's sincere.

Post reply on HN