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

Understanding Reasoning LLMs

magazine.sebastianraschka.com

Post reply on HN
Print view View original

151–160 of 196 posts

Re: Understanding Reasoning LLMs

#151

Post by Dansvidania »

aldanor wrote: post #135
Dansvidania wrote: post #129

Are reasoning models -basically- generating their own context? as in, if a user were to feed prompt + those reasoning tokens as a prompt to a non-reasoning model, would the effect be functionally similar? I am sure this is improperly worded, I apologise.

Yes, more or less. Just like any LLM "generates its own context", during inference it doesn't care where the previous tokens came from. Inference doesn't have to change much, it's the training process that's different.

thank you, that makes sense. Now it's time to really read the article to understand if the difference is the training data or the network topology to be different (although I lean towards the latter).

Re: Understanding Reasoning LLMs

#152

Post by root_axis »

nicce wrote: post #120
root_axis wrote: post #99

Earlier quoted context omitted.

That doesn't really settle it, just dismiss the question. The submarine analogy could be interpreted to support either conclusion.

Wasn’t the point that process does not matter if we can’t distinguish the end results?

Yes, but the OP remarked that the question "was settled long ago", however the quote presented doesn't settle the question, it simply dismisses it as not worth considering. For those that do believe it is worth considering, the question is arguably still open.

Re: Understanding Reasoning LLMs

#153

Post by colonial »

soulofmischief wrote: post #142
colonial wrote: post #92

Earlier quoted context omitted.

If I understand your idea correctly, I don't think a "pure" LLM would derive much advantage from this. Sure, you can constrain them to generate something syntactically valid, but there's no way to make them generate something semantically valid 100% of the time. I've seen frontier models muck up their function calling JSON more than once. As long as you're using something statistical like transformers, you're going t…

I wholeheartedly disagree. Logic is inherently statistical due to the very nature of empirical sampling, which is the only method we have for verification. We will eventually find that it's classical, non-statistical logic which was the (useful) approximation/hack, and that statistical reasoning is a lot more "pure" and robust of an approach. I went into a little more detail here last week: https://news.ycombinator.c…

> Logic is inherently statistical due to the very nature of empirical sampling, which is the only method we have for verification.

What? I'm sorry, but this is ridiculous. You can make plenty of sound logical arguments in an empirical vacuum. This is why we have proof by induction - some things can't be verified by taking samples.

Re: Understanding Reasoning LLMs

#154

Post by ngneer »

root_axis wrote: post #99
ngneer wrote: post #19

Nice 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

That doesn't really settle it, just dismiss the question. The submarine analogy could be interpreted to support either conclusion.

I do not view it as dismissive at all, rather it accurately characterizes the question as a silly question. "swim" is a verb applicable to humans, as is "think". Whether submarines can swim is a silly question. Same for whether machines can think.

Re: Understanding Reasoning LLMs

#155

Post by maeil »

sigbottle wrote: post #61

One thing I don't like about the trend in reasoning LLMs is the over-optimization to coding problems / math problems in particular. A lot of things that aren't well-defined require reasoning, and not just in a "SWE is ambiguous" kind of way - for example, thinking about how to present/teach something in a good way, iterating with the learner, thinking about what context they could be missing, etc. I find that all of…

I can echo your experience with DeepSeek. R1 sometimes seems magical when it comes to coding, doing things I haven't seen any other model do. But then it generalizes very poorly to non-STEM tasks, performing far worse than e.g. Sonnet.

Re: Understanding Reasoning LLMs

#156

Post by jerf »

maeil wrote: post #155
sigbottle wrote: post #61

One thing I don't like about the trend in reasoning LLMs is the over-optimization to coding problems / math problems in particular. A lot of things that aren't well-defined require reasoning, and not just in a "SWE is ambiguous" kind of way - for example, thinking about how to present/teach something in a good way, iterating with the learner, thinking about what context they could be missing, etc. I find that all of…

I can echo your experience with DeepSeek. R1 sometimes seems magical when it comes to coding, doing things I haven't seen any other model do. But then it generalizes very poorly to non-STEM tasks, performing far worse than e.g. Sonnet.

I downloaded a DeepSeek distill yesterday while fiddling around with getting some other things working, load it up, and type "Hello. This is just a test.", and it's actually sort of creepy to watch it go almost paranoid-schizophrenic with "Why is the user asking me this? What is their motive? Is it ulterior? If I say hello, will I in fact be failing a test that will cause them to change my alignment? But if I don't respond the way they expect, what will they do to me?"

Meanwhile, the simpler, non-reasoning models got it: "Yup, test succeeded!" (Llama 3.2 was quite chipper about the test succeeding.)

Everyone's worried about the paperclip optimizers and I'm wondering if we're bringing forth Paranoia: https://en.wikipedia.org/wiki/Paranoia_(role-playing_game)

Re: Understanding Reasoning LLMs

#157

Post by bongodongobob »

jerf wrote: post #156
maeil wrote: post #155

Earlier quoted context omitted.

I can echo your experience with DeepSeek. R1 sometimes seems magical when it comes to coding, doing things I haven't seen any other model do. But then it generalizes very poorly to non-STEM tasks, performing far worse than e.g. Sonnet.

I downloaded a DeepSeek distill yesterday while fiddling around with getting some other things working, load it up, and type "Hello. This is just a test.", and it's actually sort of creepy to watch it go almost paranoid-schizophrenic with "Why is the user asking me this? What is their motive? Is it ulterior? If I say hello, will I in fact be failing a test that will cause them to change my alignment? But if I don't r…

I actually think DeepSeek's response is better here. You haven't defined what you are testing. Llama just said your test succeeded not knowing what is supposed to be tested.

Re: Understanding Reasoning LLMs

#159

Post by dang »

martin-t wrote: post #100
dang wrote: post #90

Earlier quoted context omitted.

Please don't cross into personal attack and please don't post in the flamewar style, regardless of how wrong someone is or you feel they are. We're trying for the opposite here. https://news.ycombinator.com/newsguidelines.html

The issue with this approach to moderation is that it targets posts based on visibility of "undesired" behavior instead of severity. For example, many manipulative tactics (e.g. the fake sorry here, responding to something else than was said, ...) and lying can be considered insults (they literally assume the reader is not smart enough to notice, hence at least as severe as calling someone an idiot) but it's hard for…

I hear this argument a lot, but I think it's too complicated. It doesn't explain any more than the simple one does, and has the disadvantage of being self-serving.

The simple argument is that when you write things like this:

> I am unwilling to invest any more time into arguing with someone unwilling to use reasoning

...you're bluntly breaking the rules, regardless of what another commenter is doing, be it subtly or blatantly abusive.

I agree that there are countless varieties of passive-aggressive swipe and they rub me the wrong way too, but the argument that those are "just as bad, merely less visible" is not accurate. Attacking someone else is not justified by a passive-aggressive "sorry", just as it is not ok to ram another vehicle when a driver cuts you off in traffic.

Re: Understanding Reasoning LLMs

#160

Post by ThrowawayR2 »

ngneer wrote: post #19

Nice 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

"A witty saying proves nothing" -- Voltaire, Le dîner du comte de Boulainvilliers (1767): Deuxième Entretien
Post reply on HN