62 comments

[ 26.0 ms ] story [ 35.7 ms ] thread
Do they ?
Of course they do, how else do you think they manage to implement new features in large codebases, or to prove new theorems? But you don't even have to assume they do because of the results- you can read their chain of thought.
they don't tho
For the love of all that is sacred, please stop doing this. I'm begging you. The whole social media landscape is dying and you are creating a throwaway to participate in ruining this small corner. I assume this is not your first. And no one is convinced by this! The guidelines are there for your benefit as well. You achieve nothing but hastening the destruction of one of the last half-decent communities. Sorry for the melodrama.
this corner sucks already
The top two comments in this thread agree with the point you just made. This is true of essentially any thread on the subject. If this place sucks, it would have to be because of people like you. If not, you in particular may not be very good at noticing.
[delayed]
It's indeed so powerful that even my compiler and my unit tests fell victim of this delusion.
The article answers this question, at least to the extent it can be answered, at this time.

We see some signs of reasoning, but also we understand little about how they work.

Do we see actual signs of reasoning or is it anthropomorphism? We have an innate tendency to do so as humans.
Yes, we do see signs of actual reasoning, see the papers linked in the article. (There are many others too.)

Yes, we have a tendency to anthropomorphize, but (most) researchers are aware of this.

Yes, there is an LLM feature that we have anthropomorphized as "reasoning" or "thinking", where an LLM has a scratch space where it can dump tokens that help to improve the final output.
> that help to improve the final output

Do they actually help? Are you sure?

[delayed]
We've edited the title now in the hope of nudging the discussion in a more substantive direction.
My toaster doesn't reason, and neither do the current clankers.
How'd your toaster do at IMO last year?
One plausible reason I thought of that we may not understand neural nets is that by their nature their power grows with ever-more complex connections and weights.

So it is like the opposite of logical systems, in that the very design of neural net architecture is a mess of parameter "spaghetti code" which renders the entire thing a metaphorical encrypted black box. The more powerful an AI/AGI the more this would be the case, and this is analogous a complexity curve.

And so any effort to make sense of such black box computation would be like trying to reverse entropy, analogous to trying to recover information lost in waste heat. And that could be one fundamental barrier to understanding both human and artificial brains alike, relative to their internal complexity.

(Just thinking aloud my handwavy pet theory recently, I am not an expert and could be totally mistaken on this)

You dont have to understand chemistry to be a good cook tho.
They dont. They have input that runs through a invisible stochastic canyon. As long as there is previous experience the stochastic canyon never ends. If there is none or isignificant one, or it runs out of tokkens, it hallucinates and the illusion falls apart. There is no reasoning, just the invisible grand canyon of all of human experience and knowledge. PS: try to get it to retell you a clichee movie or book and you can see life near the end, how the delta of all the same movies opens up into wildly different endings.

To advance further it would need the ability to abstract away the general situation shape and pattern recognize similar situations.

(comment deleted)
Stochastic gradient descent can be likened to traveling down a canyon. But inference? Hardly.
It’s curious how they solve unsolved math problems without reasoning. Maybe I have a different definition of reasoning than you.
Jury is still out on this one.

This needs to be routine to be given asevidence…

…Unless you know exactly how the llm was trained and then how it was applied

Here is Yuji Tachikawa from Japan (Mathematical Physics, String Theory, QFT) on recent progress in his own work using Fable 5 :

"I've been trying out Claude Fable recently, and last night, on a whim, I showed it my research notes about a collaborative project that's seen no progress in the past six months or so and asked for its thoughts. To my surprise, it made a non-trivial observation and essentially solved it."

"I was also surprised that it was using sympy to automatically write code and verify his own predictions."

"Fable probably seems like it properly understands string theory and has intuition too—that's my impression"

There is a streamer who plays Diablo 2 by listening to the AI advice and it is quite funny since it is pretty clear that most of the advice is an amalgamation of random, often incorrect advicem

I wonder if it is the same for programming or not, but I vibe coded an android app just to see if I can and it just works. It required a lot of "build the code and correct the errors" pushing though. For example requested code in kotlin but received something else.

As somebody who uses Claude heavily and heavily plays D2R it’s clear he wasn’t using Claude opus…… maybe Haiku or something. Opus isn’t as brain dead as what was being displayed
(comment deleted)
Compression is the trick. Its even philosophed about if compression = intelligence.

The LLM has to compress everyy question/prompt into its system. It does so by creating rules and ways of processing data (this can lead to AGI, world models or an architecture of sub architectures like an LLM + something else). So if it should respond in a way that only reasoning people can achieve, it might be able to learn a representation of what we call reasoning.

It read enough text in itself to even know about the concept of reasoning and how you would do that.

Even if this is only stochastic, it shouldn't be so devalued as your comment comes across.

Who says that we are doing anything more magic?

It's probably helpful in this discussion to make a difference between two definitions of reasoning:

1. phenomenal reasoning, requiring consciousness and subjective experience

2. functional reasoning, transforming premises into conclusions using logic

I think you are attacking this using definition 1, whereas the article is obviously aiming at a different type of reasoning, and trying to formalize what is actually going on. It seems to be a genuine effort.

>1. phenomenal reasoning, requiring consciousness and subjective experience

I think it is incumbent upon anyone arguing that something does not posses any given property to provide a non-circular definition of what it is that they are declaring an absence of.

All of the descriptions of experiential reasoning are usually defined in terms of rephrasing of the claim "true understanding", "conscious", "aware", "knowing" all hinge on a synonymous aspect of the words that try and shift the responsibly of explanation to the next term used in a cyclic manner.

For the weaker sense of reasoning, there simply isn't any argument that it is not happening. A calculator can perform the weaker sense. The analysis of this aspect of LLMs is purely a question of how, not what.

When a mathematician reads a hundred-year-old math paper, it seems like they are reproducing in their head the reasoning of someone who died long ago. That is, reasoning can be written down and replicated.

If that works, I think it's fair to say that LLM's are inanimate processes can generate real reasoning. You can tell when you read it and it makes sense.

There are likely some kinds of reasoning that can't be written down, as well as other forms of understanding, but they also don't replicate nearly as easily.

With that definition, computers don't play chess, they just move the pieces using some weights and backtracking.
i love how anthropic puts out some bs like this every few weeks 'we saw some red bridge lights blinking in model weights when someone mentions sfo. Arent they just like us?"
(comment deleted)
Well, if you read the foundational paper 'All you need is Attention', review the full stack trace of any LLM system call, and have insight to the ad hoc training process to ingest additional data and knowledge, you will gain greater understanding.

If you enjoy such content, please like and subscribe to my channel: xxXNoobSmasher69Xxx

This article is not about "reasoning" in the abstract, philosophical sense but is talking about "mechanistic interpretability" research. The title is more like, "can we understand if the 'knowledge' encoded into a neural networks actually corresponds to reasoning-like concepts" and doing that with actual experiments like tweaking weights and activations.

There's an interesting example where researchers saw a model approached clock time calculations and calendar month-day calculations using the same methodology. So then is this because an underlying concept of "cyclical measures" has emerged in the network?

Thanks - I've attempted to put that in the title above, in the hope of representing the article accurately.

(The trouble with a baity title like "Can We Understand How Large Language Models Reason?" is that it generates a barrage of shallow, reflexive responses having little to do with the article. What we want on HN are curious, reflexive responses instead - https://hn.algolia.com/?dateRange=all&page=0&prefix=true&sor....)

I personally would not look for the way they reason in the weights, at least not directly. In principle I could replace a large language model with a map from all possible input strings to output token or output token distribution without any weights. I have a hard time imagining how you would even tell, at the level of weights and activations, if the next token being the is the result of some proper reasoning or a hallucination. But those weights do not exist for the sake of it, they encode a lot of text the model has seen during training, and I would imagine this is what drives the reasoning. Can you evaluate the following polynomial ... will be related to To evaluate a polynomial ... seen in the training data. This is the level at which I would look for the reasoning, memorized patterns how to do specific things, maybe with some kind of placeholder variables for generalization. Ultimately such a structure would of course also be represented in the weights but I could imagine that this makes it unnecessary hard to understand. Or maybe not, maybe the learned patterns are so complex that they do not have a simple representation.
I also suspect the learned patterns are not necessarily efficient, though might be by accident.

One could “learn” addition by memorizing a truth table instead of understanding the concept… The truth table itself wouldn’t have much meaning.

> In principle I could replace a large language model with a map from all possible input strings to output token or output token distribution without any weights.

What is an output token distribution except a set of weights?

>“Mechanistic interpretability will probably never reduce large language models to a few simple equations,” Icard concluded, “but it may gradually turn deep neural networks into systems whose hidden algorithms can at least partly be understood.”

what is the basis for this optimism ?

The optimism is based on the successes so far, some of which are described in this article. Scientists have made progress here.
no they havent . success so far is totally meaningless and doesn't imply any sort of upward slope .
The researchers in the field disagree with you. Look at conferences like NeurIPS and ICLR to see a steady stream of incremental progress in this area.
What would real progress look like?
[stub for offtopicness]

[[All: please don't post shallow-generic reactions to baity titles. Those are basically the same thing, a la https://en.wikipedia.org/wiki/Rubin_vase, and we're trying for something more substantive here.]]

Original HN title: "Can We Understand How Large Language Models Reason?"
I also calculate six months from August as 8+6=14mod12. I wonder if anyone does it differently, this seems like the most plausible technique.
To calculate +/- 3/6/9 months I shift by seasons. 3rd month of summer becomes 3rd month of winter.

That works well cause all months live in a primitive memory palace in my head: an analogue clock face with July at 12 and January at 6. So shifting by 6 means rotating the clock hand from 11 to 5 and immediately visualising what month it falls on.

This might sound inefficient to an LLM but human brains had image processing before language.

For me: January = up, April = left, July = down, October = right.

Never sure why I did this association, maybe it comes from a drawing in a book I read when I was six or somthn?