Amazing accomplishments by brightest minds only to be used to write history by the stupidest people.
Understanding Reasoning LLMs
11–20 of 196 posts
Re: Understanding Reasoning LLMs
#12I like Raschka's writing, even if he is considerably more optimistic about this tech than I am. But I think it's inappropriate to claim that models like R1 are "good at deductive or inductive reasoning" when that is demonstrably not true, they are incapable of even the simplest "out-of-distribution" deductive reasoning: https://xcancel.com/JJitsev/status/1883158738661691878 They are certainly capable of doing is a wi…
> But I think it's inappropriate to claim that models like R1 are "good at deductive or inductive reasoning" when that is demonstrably not true, they are incapable of even the simplest "out-of-distribution" deductive reasoning: https://xcancel.com/JJitsev/status/1883158738661691878
Your link says that R1, not all models like R1, fails at generalization.
Of particular note:
> We expose DeepSeek R1 to the variations of AIW Friends problem and compare model behavior to o1-preview, o1-mini and Claude 3.5 Sonnet. o1-preview handles the problem robustly, DeepSeek R1 shows strong fluctuations across variations with distribution very similar to o1-mini.
Re: Understanding Reasoning LLMs
#13There are no LLMs that reason, its an entirely different statistical process as compared to human reasoning.
Re: Understanding Reasoning LLMs
#14Great post, but every time I read something like this I feel like I am living in a prequel to the Culture.
Re: Understanding Reasoning LLMs
#15Is there any work being done in training LLMs on more restricted formal languages? Something like a constraint solver or automated theorem prover, but much lower level. Specifically something that isn't natural language. That's the only path I could see towards reasoning models being truly effective I know there is work being done with e.g. Lean integration with ChatGPT, but that's not what I mean exactly -- there's…
In my mind, the pure reinforcement learning approach of DeepSeek is the most practical way to do this. Essentially it needs to continually refine and find more sound(?) subspaces of the latent (embedding) space. Now this could be the subspace which is just Python code (or some other human-invented subspace), but I don't think that would be optimal for the overall architecture. The reason why it seems the most reasona…
fwiw, most people don't really grok the power of latent space wrt language models. Like, you say it, I believe it, but most people don't really grasp it.
Re: Understanding Reasoning LLMs
#16I like Raschka's writing, even if he is considerably more optimistic about this tech than I am. But I think it's inappropriate to claim that models like R1 are "good at deductive or inductive reasoning" when that is demonstrably not true, they are incapable of even the simplest "out-of-distribution" deductive reasoning: https://xcancel.com/JJitsev/status/1883158738661691878 They are certainly capable of doing is a wi…
> But I think it's inappropriate to claim that models like R1 are "good at deductive or inductive reasoning" when that is demonstrably not true, they are incapable of even the simplest "out-of-distribution" deductive reasoning: https://xcancel.com/JJitsev/status/1883158738661691878 Your link says that R1, not all models like R1, fails at generalization. Of particular note: > We expose DeepSeek R1 to the variations of…
The way the authors talk about LLMs really rubs me the wrong way. They spend more of the paper talking up the 'claims' about LLMs that they are going to debunk than actually doing any interesting study.
They came into this with the assumption that LLMs are just a cheap trick. As a result, they deliberately searched for an example of failure, rather than trying to do an honest assessment of generalization capabilities.
Re: Understanding Reasoning LLMs
#17I like Raschka's writing, even if he is considerably more optimistic about this tech than I am. But I think it's inappropriate to claim that models like R1 are "good at deductive or inductive reasoning" when that is demonstrably not true, they are incapable of even the simplest "out-of-distribution" deductive reasoning: https://xcancel.com/JJitsev/status/1883158738661691878 They are certainly capable of doing is a wi…
>But I think it's inappropriate to claim that models like R1 are "good at deductive or inductive reasoning" when that is demonstrably not true, they are incapable of even the simplest "out-of-distribution" deductive reasoning:
That's not actually what your link says. The tweet says that it solves the simple problem (that they originally designed to foil base LLMs) so they had to invent harder problems until they found one it could not reliably solve.
Re: Understanding Reasoning LLMs
#18I like Raschka's writing, even if he is considerably more optimistic about this tech than I am. But I think it's inappropriate to claim that models like R1 are "good at deductive or inductive reasoning" when that is demonstrably not true, they are incapable of even the simplest "out-of-distribution" deductive reasoning: https://xcancel.com/JJitsev/status/1883158738661691878 They are certainly capable of doing is a wi…
The other day I fed a complicated engineering doc for an architectural proposal at work into R1. I incorporated a few great suggestions into my work. Then my work got reviewed very positively by a large team of senior/staff+ engineers (most with experience at FAANG; ie credibly solid engineers). R1 was really useful! Sorry you don’t like it but I think it’s unfair to say it sucks at reasoning.
Re: Understanding Reasoning LLMs
#19Nice article.
>Whether and how an LLM actually "thinks" is a separate discussion.
The "whether" is hardly a discussion at all. Or, at least one that was settled long ago.
"The question of whether a computer can think is no more interesting than the question of whether a submarine can swim."
--Edsger Dijkstra
Re: Understanding Reasoning LLMs
#20doesn't it seem like these models are getting to the point where even conceiving their training and development is less and less possible for the general public? I mean, we already knew only a handful of companies with capital could train them, but at least the principles, algorithms, etc. were accessible to individuals who wanted to create their own - much simpler - models. it seems that era is quickly ending, and w…
Recent developments like V3, R1 and S1 are actually clarifying and pointing towards more understandable, efficient and therefore more accessible models.