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

Procedural knowledge in pretraining drives reasoning in large language models

arxiv.org

Post reply on HN
Print view View original

101–104 of 104 posts

Re: Procedural knowledge in pretraining drives reasoning in large language models

#101

Post by YetAnotherNick »

MurizS wrote: post #43
strken wrote: post #25

Earlier quoted context omitted.

That sounds interesting, but I'm a layman and don't know anything about it. Can you provide a link? I was able to find https://arxiv.org/abs/2408.10914 , but I don't have the context to know whether it's the paper you're talking about.

I think GP was probably referring to "Scaling Data-Constrained Language Models" (2305.16264) from NeurIPS 2023, which looked first at how to optimally scale LLMs when training data is limited. There is a short section on mixing code (Python) into the training data and the effect this has on performance on e.g. natural language tasks. One of their findings was that training data can be up to 50% code without actually…

Also GPT-3.5 was another extreme if I remember correctly. They first trained only on code then they trained on other text. I can't seem to find the source though.

Re: Procedural knowledge in pretraining drives reasoning in large language models

#102

Post by eru »

naasking wrote: post #80
eru wrote: post #57

Earlier quoted context omitted.

> Even the current limited models change the economics dramatically. Yes, though at the moment they hype is still a lot bigger than the impact. But I am fairly confident that even without any new technical ideas for the networks themselves, we will see a lot more economic impact over the next few years, as people work out how to use these new tools. (Of course, the networks will also evolve still.)

I think the impact is already understated. Every non-technical person I know that's still working has used ChatGPT for work at some point, and quite a few of them are using it regularly. And I'm nowhere near Silicon Valley or any serious tech hub.

Yes, they are great for helping with writer's block or for replacing a Google search.

But there's a lot of stuff they can't really do (in their current form), or can't do reliable, yet.

> Every non-technical person I know that's still working has used ChatGPT for work at some point, and quite a few of them are using it regularly. And I'm nowhere near Silicon Valley or any serious tech hub.

Yes, that makes me optimistic for their future, too.

Re: Procedural knowledge in pretraining drives reasoning in large language models

#103

Post by fragmede »

rors wrote: post #26

It seems obvious to me that LLMs wouldn't be able to find examples of every single problem posed to them in training data. There wouldn't be enough examples for the factual look up needed in an information retrieval style search. I can believe that they're doing some form of extrapolation to create novel solutions to posed problems. It's interesting that this paper doesn't contradict the conclusions of the Apple LLM…

> It's a term coined by LLM companies to evoke an almost emotional response on how we talk about this technology.

Anthropomorphizing computers has been happening long before ChatGPT. No one thinks their computer is actually eating their homework when they say that to refer to the fact that their computer crashed and their document wasn't saved, it's just an easy way to refer to the thing it just did. Before LLMs, "the computer is thinking" wasn't an unuttered sentence. Math terms aren't well known to everybody, so saying Claudr is dot-producting an essay for me, or I had ChatGPT dot-product that letter to my boss, no one knows that a dot product is, so even if that's a more technically accurate verb, who's gonna use it? So while AI companies haven't done anything to promote usage of different terms than "thinking" and "reasoning", it's also because those are the most handy terms. It "thinks" there are two R's in strawberries. It dot-products there are two R's in strawberries. It also matrix multiplies, occasionally softmaxes; convolves. But most people aren't Terence Tao and don't have a feel for when something's softmaxing because what even does that mean?

Re: Procedural knowledge in pretraining drives reasoning in large language models

#104

Post by cscurmudgeon »

XenophileJKO wrote: post #50
cscurmudgeon wrote: post #47

Earlier quoted context omitted.

> We hold AI to a pretty high standard of correctness, as we should, but humans are not that reliable on matters of fact, let alone on rigor of reasoning. I never understood this line of reasoning. 1. Humans can't run faster than 30 mph. 2. Therefore we can't complain if cars/trains/transport always go slower than 30 mph. These comparisons also hide that we are comparing best of AI (massive LLMs) with median/average…

The whole social dynamic of this conversation is amazing. How fast complacency happened. In 2010 if you told me I could get a model to respond approximately as intelligently as a low intelligence human, I would be amazed. As a matter of perspective,I am still amazed. At the same time I see such negative sentiment around the capabilities at their current limits. We are reaching an era of commodified intelligence, whic…

Nobody is disputing that. Just because we have gone to the Moon doesn’t imply we are at Mars.
Post reply on HN