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

971–980 of 1001 posts

Re: Learning to Reason with LLMs

#971

Post by valval »

deisteve wrote: post #651
thomasahle wrote: post #281

Earlier quoted context omitted.

As good as Claude has gotten recently in reasoning, they are likely using RL behind the scenes too. Supposedly, o1/strawberry was initially created as an engine for high-quality synthetic reasoning data for the new model generation. I wonder if Anthropic could release their generator as a usable model too.

while i was initially excited now im having second thoughts after seeing the experiments run by people in the comments here on X I see a totally different energy more about hyping it on HN I see reserved and collected take which I trust more. I do wonder why they chose gpt4o which I never bother to use for coding. Claude is still king and looks like I won't have to subscribe to ChatGPT Plus seeing it fail on some of…

I think people are wrong just about as often here as anywhere else on the internet, but with more confidence. Averaging HN comments would just produce outputs similar to rudimentary LLMs with a bit snobbier of a tone, I imagine.

Re: Learning to Reason with LLMs

#973

Post by valval »

dinobones wrote: post #4

Generating more "think out loud" tokens and hiding them from the user... Idk if I'm "feeling the AGI" if I'm being honest. Also... telling that they choose to benchmark against CodeForces rather than SWE-bench.

They’re running a business. They don’t owe you their trade secrets.

Re: Learning to Reason with LLMs

#975

Post by suziemanul »

bjornsing wrote: post #276
ARandumGuy wrote: post #137

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…

So now it’s a question of how fast the AGI will run? :)

This is still the missing piece of the puzzle.

Re: Learning to Reason with LLMs

#978

Post by ValentinA23 »

max_entropy wrote: post #960
kmoser wrote: post #958

Earlier quoted context omitted.

Am I right that this CoT is not actual reasoning in the same way that a human would reason, but rather just a series of queries to the model that still return results based on probabilities of tokens?

Tough question (for me). Assuming the model is producing its own queries, am I wrong to wonder how it's fundamentally different from human reasoning?

Maybe the model doesn't do multiple queries but just one long query guided by thought tokens.

Re: Learning to Reason with LLMs

#979

Post by theaussiestew »

wesleyyue wrote: post #889
TheMiddleMan wrote: post #791

Earlier quoted context omitted.

Trying out Double now. o1 did a significantly better job converting a JavaScript file to TypeScript than Llama 3.1 405B, GitHub Copilot, and Claude 3.5. It even simplified my code a bit while retaining the same functionality. Very impressive. It was able to refactor a ~160 line file but I'm getting an infinite "thinking bubble" on a ~420 line file. Maybe something's timing out with the longer o1 response times?

> Maybe something's timing out with the longer o1 response times? Let me look into this – one issue is that OpenAI doesn't expose a streaming endpoint via the API for o1 models. It's possible there's an HTTP timeout occurring in the stack. Thanks for the report

I've gotten this as well, on very short code snippets. I type in a prompt and then sometimes it doesn't respond with anything, it gets stuck on the thinking, and other times it gets halfway through the response generation and then it gets stuck as well.

https://chatgpt.com/c/66e3a628-2814-8012-a6c5-33721b78cb99

Post reply on HN