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

Learning to Reason with LLMs

openai.com

Post reply on HN
Print view View original

131–140 of 1001 posts

Re: Learning to Reason with LLMs

#131

Post by rfw300 »

afavour wrote: post #73
rfw300 wrote: post #39

A lot of skepticism here, but these are astonishing results! People should realize we’re reaching the point where LLMs are surpassing humans in any task limited in scope enough to be a “benchmark”. And as anyone who’s spent time using Claude 3.5 Sonnet / GPT-4o can attest, these things really are useful and smart! (And, if these results hold up, O1 is much, much smarter.) This is a nerve-wracking time to be a knowled…

> People should realize we’re reaching the point where LLMs are surpassing humans in any task limited in scope enough to be a “benchmark”. Can you explain what this statement means? It sounds like you're saying LLMs are now smart enough to be able to jump through arbitrary hoops but are not able to do so when taken outside of that comfort zone. If my reading is correct then it sounds like skepticism is still warrante…

I think what I’m saying is a bit more nuanced than that. LLMs currently struggle with very “wide”, long-run reasoning tasks (e.g., the evolution over time of a million-line codebase). That isn’t because they are secretly stupid and their capabilities are all hype, it’s just that this technology currently has a different balance of strengths and weaknesses than human intelligence, which tends to more smoothly extrapolate to longer-horizon tasks.

We are seeing steady improvement on long-run tasks (SWE-Bench being one example) and much more improvement on shorter, more well-defined tasks. The latter capabilities aren’t “hype” or just for show, there really is productive work like that to be done in the world! It’s just not everything, yet.

Re: Learning to Reason with LLMs

#133

Post by logicchains »

arresin wrote: post #119

> Unless otherwise specified, we evaluated o1 on the maximal test-time compute setting. Maximal test time is the maximum amount of time spent doing the “Chain of Thought” “reasoning”. So that’s what these results are based on. The caveat is that in the graphs they show that for each increase in test-time performance, the (wall) time / compute goes up exponentially . So there is a potentially interesting play here. Th…

Surprising that at run time it needs an exponential increase in thinking to achieved a linear increase in output quality. I suppose it's due to diminishing returns to adding more and more thought.

Re: Learning to Reason with LLMs

#136

Post by gradus_ad »

dinobones wrote: post #60
thelastparadise wrote: post #41

Earlier quoted context omitted.

Why not? Isn't that basically what humans do? Sit there and think for a while before answering, going down different branches/chains of thought?

This new approach is showing: 1) The "bitter lesson" may not be true, and there is a fundamental limit to transformer intelligence. 2) The "bitter lesson" is true, and there just isn't enough data/compute/energy to train AGI. All the cognition should be happening inside the transformer. Attention is all you need. The possible cognition and reasoning occurring "inside" in high dimensions is much more advanced than any…

Does that mean human intelligence is cheapened when you talk out a problem to yourself? Or when you write down steps solving a problem?

It's the exact same thing here.

Re: Learning to Reason with LLMs

#137

Post by ARandumGuy »

One thing that makes me skeptical is the lack of specific labels on the first two accuracy graphs. They just say it's a "log scale", without giving even a ballpark on the amount of time it took.

Did the 80% accuracy test results take 10 seconds of compute? 10 minutes? 10 hours? 10 days? It's impossible to say with the data they've given us.

The coding section indicates "ten hours to solve six challenging algorithmic problems", but it's not clear to me if that's tied to the graphs at the beginning of the article.

The article contains a lot of facts and figures, which is good! But it doesn't inspire confidence that the authors chose to obfuscate the data in the first two graphs in the article. Maybe I'm wrong, but this reads a lot like they're cherry picking the data that makes them look good, while hiding the data that doesn't look very good.

Re: Learning to Reason with LLMs

#138

Post by ramadis »

valine wrote: post #8

The model performance is driven by chain of thought, but they will not be providing chain of thought responses to the user for various reasons including competitive advantage. After the release of GPT4 it became very common to fine-tune non-OpenAI models on GPT4 output. I’d say OpenAI is rightly concerned that fine-tuning on chain of thought responses from this model would allow for quicker reproduction of their resu…

It'd be helpful if they exposed a summary of the chain-of-thought response instead. That way they'd not be leaking the actual tokens, but you'd still be able to understand the outline of the process. And, hopefully, understand where it went wrong.

Re: Learning to Reason with LLMs

#139

Post by logicchains »

islewis wrote: post #124

My first interpretation of this is that it's jazzed-up Chain-Of-Thought. The results look pretty promising, but i'm most interested in this: > Therefore, after weighing multiple factors including user experience, competitive advantage, and the option to pursue the chain of thought monitoring, we have decided not to show the raw chains of thought to users. Mentioning competitive advantage here signals to me that OpenA…

>my gut reaction is this negatively impacts model usability, but i'm having a hard time putting my finger on why.

If the model outputs an incorrect answer due to a single mistake/incorrect assumption in reasoning, the user has no way to correct it as it can't see the reasoning so can't see where the mistake was.

Post reply on HN