current AI models are searching engines that can somewhat extrapolate data and use in the current context, that's pretty much it
Recent AI model progress feels mostly like bullshit
241–250 of 478 posts
Re: Recent AI model progress feels mostly like bullshit
#242Earlier quoted context omitted.
LLMs are capable of playing chess and 3.5 turbo instruct does so quite well (for a human) at 1800 ELO. Does this mean they can truly reason now ? https://github.com/adamkarvonen/chess_gpt_eval
My point wasn't chess specific or that they couldn't have specific training for it. It was a more general "here is something that LLMs clearly aren't being trained for currently, but would also be solvable through reasoning skills" Much in the same way a human who only just learnt the rules but 0 strategy would very, very rarely lose here These companies are shouting that their products are passing incredibly hard ex…
>If an LLM is trained for chess then its performance would just come from memorization, not any kind of "reasoning".
If you think you can play chess at that level over that many games and moves with memorization then i don't know what to tell you except that you're wrong. It's not possible so let's just get that out of the way.
>These companies are shouting that their products are passing incredibly hard exams, solving PHD level questions, and are about to displace humans, and yet they still fail to crush a random-only strategy chess bot? How does this make any sense?
Why doesn't it ? Have you actually looked at any of these games ? Those LLMs aren't playing like poor reasoners. They're playing like machines who have no clue what the rules of the game are. LLMs learn by predicting and failing and getting a little better at it, repeat ad nauseum. You want them to learn the rules of a complex game ? That's how you do it. By training them to predict it. Training on chess books just makes them learn how to converse about chess.
Humans have weird failure modes that are odds with their 'intelligence'. We just choose to call them funny names and laugh about it sometimes. These Machines have theirs. That's all there is to it. The top comment we are both replying to had gemini-2.5-pro which released less than 5 days later hit 25% on the benchmark. Now that was particularly funny.
Re: Recent AI model progress feels mostly like bullshit
#243Earlier quoted context omitted.
> within a week How do we know that Gemini 2.5 wasn't specifically trained or fine-tuned with the new questions? I don't buy that a new model could suddenly score 5 times better than the previous state-of-the-art models.
They retrained their model less than a week before its release, just to juice one particular nonstandard eval? Seems implausible. Models get 5x better at things all the time. Challenges like the Winograd schema have gone from impossible to laughably easy practically overnight. Ditto for "Rs in strawberry," ferrying animals across a river, overflowing wine glass, ...
The "ferrying animals across a river" problem has definitely not been solved, they still don't understand the problem at all, overcomplicating it because they're using an off-the-shelf solution instead of actual reasoning:
o1 screwing up a trivially easy variation: https://xcancel.com/colin_fraser/status/1864787124320387202
Claude 3.7, utterly incoherent: https://xcancel.com/colin_fraser/status/1898158943962271876
DeepSeek: https://xcancel.com/colin_fraser/status/1882510886163943443#...
Overflowing wine glass also isn't meaningfully solved! I understand it is sort of solved for wine glasses (even though it looks terrible and unphysical, always seems to have weird fizz). But asking GPT to "generate an image of a transparent vase with flowers which has been overfilled with water, so that water is spilling over" had the exact same problem as the old wine glasses: the vase was clearly half-full, yet water was mysteriously trickling over the sides. Presumably OpenAI RLHFed wine glasses since it was a well-known failure, but (as always) this is just whack-a-mole, it does not generalize into understanding the physical principle.
Re: Recent AI model progress feels mostly like bullshit
#244Earlier quoted context omitted.
"Is Paul Newman known for having had problems with alcohol?" https://chatgpt.com/share/67f332e5-1548-8012-bd76-e18b3f8d52... Your query indeed answers "...not widely known..." "Did Paul Newman have problems with alcoholism?" https://chatgpt.com/share/67f3329a-5118-8012-afd0-97cc4c9b72... "Yes, Paul Newman was open about having struggled with alcoholism" What's the issue? Perhaps Paul Newman isn't _famous_ ("known") f…
Counterpoint: Paul Newman was absolutely a famous drunk, as evidenced by this Wikipedia page.* Any query for "paul newman alcohol" online will return dozens of reputable sources on the topic. Your post is easily interpretable as handwaving apologetics, and it gives big "Its the children who are wrong" energy. * https://en.wikipedia.org/wiki/Newman_Day
"Paul Newman alcohol" is just showing you results where those words are all present, it's not really implying how widely known it is.
Re: Recent AI model progress feels mostly like bullshit
#245Earlier quoted context omitted.
> That might be overstating it, at least if you mean it to be some unreplicable feat. I mean, surely there's a reason you decided to mention 3.5 turbo instruct and not.. 3.5 turbo? Or any other model? Even the ones that came after? It's clearly a big outlier, at least when you consider "LLMs" to be a wide selection of recent models. If you're saying that LLMs/transformer models are capable of being trained to play ch…
I mentioned it because it's the best example. One example is enough to disprove the "not capable of". There are other examples too. >I think AstroBen was pointing out that LLMs, despite having the ability to solve some very impressive mathematics and programming tasks, don't seem to generalize their reasoning abilities to a domain like chess. That's surprising, isn't it? Not really. The LLMs play chess like they have…
> One example is enough to disprove the "not capable of" nonsense. There are other examples too.
Gotcha, fair enough. Throw enough chess data in during training, I'm sure they'd be pretty good at chess.
I don't really understand what you're trying to say in your next paragraph. LLMs surely have plenty of training data to be familiar with the rules of chess. They also purportedly have the reasoning skills to use their familiarity to connect the dots and actually play. It's trivially true that this issue can be plastered over by shoving lots of chess game training data into them, but the success of that route is not a positive reflection on their reasoning abilities.
Re: Recent AI model progress feels mostly like bullshit
#246Earlier quoted context omitted.
I don't know why anyone is surprised that a statistical model isn't getting 100% accuracy. The fact that statistical models of text are good enough to do anything should be shocking.
I think the surprising aspect is rather how people are praising 80-90% accuracy as the next leap in technological advancement. Quality is already in decline, despite LLMs, and programming was always a discipline where correctness and predictability mattered. It's an advancement for efficiency, sure, but on the yet unknown cost of stability. I'm thinking about all simulations based on applied mathematical concepts and…
You're completely correct, of course. The issue is that most people are not looking for quality, only efficiency. In particular, business owners don't care about sacrificing some correctness if it means they can fire slews of people. Worse, gullible "engineers" that should be the ones prioritizing correctness are so business-brainwashed themselves that they like wise slop up this nonsense at the expense of sacrificing their own concern for the only principles that even made the software business remotely close to being worthy of the title "engineering".
Re: Recent AI model progress feels mostly like bullshit
#247It seems like the models are getting more reliable at the things they always could do, but they’re not showing any ability to move past that goalpost. Whereas in the past, they could occasionally write some very solid code, but often return nonsense, the nonsense is now getting adequately filtered by so-called “reasoning”, but I see no indication that they could do software design. > how the hell is it going to devel…
> Why on earth do people want AI to do either of these things?
This is the really important question, and the only answer I can drum up is that people have been fed a consistent diet of propaganda for decades centered around a message that ultimately boils down to a justification of oligarchy and the concentration of wealth. That and the consumer-focus facade makes people think the LLMS are technology for them—they aren't. As soon as these things get good enough business owners aren't going to expect workers to use them to be more productive, they are just going to fire workers and/or use the tooling as another mechanism by which to let wages stagnate.
Re: Recent AI model progress feels mostly like bullshit
#248The biggest story in AI was released a few weeks ago but was given little attention: on the recent USAMO, SOTA models scored on average 5% (IIRC, it was some abysmal number). This is despite them supposedly having gotten 50%, 60% etc performance on IMO questions. This massively suggests AI models simply remember the past results, instead of actually solving these questions. I'm incredibly surprised no one mentions th…
Nope, no LLMs reported 50~60% performance on IMO, and SOTA LLMs scoring 5% on USAMO is expected. For 50~60% performance on IMO, you are thinking of AlphaProof, but AlphaProof is not a LLM. We don't have the full paper yet, but clearly AlphaProof is a system built on top of LLM with lots of bells and whistles, just like AlphaFold is.
o1 reportedly got 83% on IMO, and 89th percentile on Codeforces.
https://openai.com/index/learning-to-reason-with-llms/
The paper tested it on o1-pro as well. Correct me if I'm getting some versioning mixed up here.
Re: Recent AI model progress feels mostly like bullshit
#249There's some interesting information and analysis to start off this essay, then it ends with: "These machines will soon become the beating hearts of the society in which we live. The social and political structures they create as they compose and interact with each other will define everything we see around us." This sounds like an article of faith to me. One could just as easily say they won't become the beating hea…
While I really want your version of the future, history and general trajectory and tendency unfortunately suggest otherwise.
Re: Recent AI model progress feels mostly like bullshit
#250Earlier quoted context omitted.
> within a week How do we know that Gemini 2.5 wasn't specifically trained or fine-tuned with the new questions? I don't buy that a new model could suddenly score 5 times better than the previous state-of-the-art models.
They retrained their model less than a week before its release, just to juice one particular nonstandard eval? Seems implausible. Models get 5x better at things all the time. Challenges like the Winograd schema have gone from impossible to laughably easy practically overnight. Ditto for "Rs in strawberry," ferrying animals across a river, overflowing wine glass, ...
>one particular nonstandard eval
A particular nonstandard eval that is currently top comment on this HN thread, due to the fact that, unlike every other eval out there, LLMs score badly on it?
Doesn't seem implausible to me at all. If I was running that team, I would be "Drop what you're doing, boys and girls, and optimise the hell out of this test! This is our differentiator!"