46 points by adunk 2 hours ago | 11 comments
antleys 16 minutes ago
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?

danbruc 2 minutes ago
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.
warumdarum 1 hour ago
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.

skybrian 1 minute ago
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.

smokel 14 minutes ago
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.

Lomlioto 19 minutes ago
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?

20 minutes ago
red75prime 41 minutes ago
Stochastic gradient descent can be likened to traveling down a billion-dimensional canyon. But inference? Hardly.
alchemist1e9 32 minutes ago
It’s curious how they solve unsolved math problems without reasoning. Maybe I have a different definition of reasoning than you.
crewindream 7 minutes ago
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

emp17344 29 minutes ago
Guess what? SAT solvers have also solved unsolved math problems. Do you believe they are “reasoning”?
wizzwizz4 17 minutes ago
The question of whether a SAT solver can reason is about as interesting as the question of whether a submarine can swim. (EWD867, EWD898)
rvba 22 minutes ago
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.

mexicojalisco 8 minutes ago
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
46 minutes ago
CrzyLngPwd 1 hour ago
My toaster doesn't reason, and neither do the current clankers.
CamperBob2 12 minutes ago
How'd your toaster do at IMO last year?
gfody 50 minutes ago
there's a 2MP about the related paper: https://www.youtube.com/watch?v=l72ufA-4SzE
calf 1 hour ago
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)

analog31 1 hour ago
Do LLMs have Qualia?
wat10000 35 minutes ago
Do people?
emp17344 22 minutes ago
Yes.
wat10000 21 minutes ago
How do you know?
otabdeveloper4 1 hour ago
They don't reason.
CamperBob2 11 minutes ago
What would change your mind?
chrisjj 1 hour ago
Clickbait article title.

The article body does not presume they reason.

JackSlateur 1 hour ago
Do they ?
azakai 1 hour ago
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.

michaelchisari 1 hour ago
Do we see actual signs of reasoning or is it anthropomorphism? We have an innate tendency to do so as humans.
blooalien 1 hour ago
> Do we see signs of reasoning or is it anthropomorphism?

This is the part that so many folks just don't seem to understand (probably because it's been labeled as "thinking" or "reasoning" mode, and people assume that words have meaning). It's not reasoning or thought. It's spewing tokens pretending to "think", but it's actually just generating extra "context" to help the final answer be more coherent. The model isn't doing anything it doesn't already do. It's just doing more of it to improve the quality of the final answer displayed to the user.

Leonard_of_Q 42 minutes ago
You're describing a process by which a 'thinking' entity uses cognition to refine a solution to a stated problem. That's a lot of words so usually we shorten this to 'reasoning'.

Do LLMs 'think'? I 'think' they do in a way. I don't really know how I think myself but I know I do and therefore I am (thanks, Descartes). I have a somewhat better grasp of the way LLMs 'think'. They do so sequentially, building a chain of descriptors which best fit the problem and the preceding descriptors. I suspect I do something not entirely dissimilar- i.e. I imagine 'worlds' which are like the current one changed in some way so they the problem I'm working on is reduced, then refine those until it is resolved - but in a massively parallel way.

blooalien 15 minutes ago
Fine. Whatever. I give up. LLMs think. Believe what you want. I literally no longer care, and this argument is beyond exhausting. Go ask the LLM to explain itself to you. It will happily spew out a pretty solid explanation of the details and math involved if you ask it the right questions in the right way. It'll also happily play along with you if you want to roleplay that it is an actual thinking machine. It's designed that way. But hey, whatever. It's a thinking intelligent machine and we're all doomed. I accept that my many decades of working with and learning about computers was wasted and I know nothing about them at all.
dataflow 42 minutes ago
Honestly, people need to get over this debate. It's pretty irrelevant in a lot of cases. When people ask "what is the model thinking?", they're really asking "what caused the model to produce this response (as opposed to a bunch of other plausible ones)?"

Whether it's thinking or word prediction or whatever you want to call it, people are trying to understand the causal chain.

throw310822 23 minutes ago
It's not just a nominalistic debate though, as the people who are vocal against the idea that LLMs might "understand" or "think" also claim that because of this, they are fundamentally limited in what they can achieve, in contrast to human beings. Therefore any possibility of actual intelligence (or even superintelligence) is, according to them, just a fantasy.
wat10000 34 minutes ago
Angry diatribes about whether submarines swim or not.
azakai 1 hour ago
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.

michaelchisari 1 hour ago
The papers linked in the article discuss the mechanical operations that simulate reasoning. Intelligence is data efficiency and I don't see a strong argument that reasoning can exist if it requires a world's worth of data.

That doesn't mean that simulated reasoning isn't useful, it's wildly useful. But a thing is not its simulation.

throw310822 8 minutes ago
> a thing is not its simulation.

"The King leaned over, looked and saw, yes, the Middle Ages simulated to a T, all digital, binary , and nonlinear, and there was the land of Dandelia, The Icicle Forest, the palace with the Helical Tower, the Aviary That Neighed, and the Treasury with a Hundred Eyes as well, and there was Ineffabelle herself, taking a slow, stochastic stroll through the simulated garden, and her circuits glowed red and gold as she picked simulated daisies, and hummed a simulated song."

(Stanislaw Lem, Cyberiad)

arcanemachiner 1 hour ago
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.
otabdeveloper4 1 hour ago
> that help to improve the final output

Do they actually help? Are you sure?

throw310822 1 hour ago
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.
chrisjj 1 hour ago
The Eliza effect.
throw310822 45 minutes ago
It's indeed so powerful that even my compiler and my unit tests fell victim of this delusion.
3848499449 1 hour ago
[flagged]
ToValueFunfetti 1 hour ago
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.
3848499449 29 minutes ago
[flagged]
ToValueFunfetti 21 minutes ago
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.
RobRivera 23 minutes ago
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

Edit: bad faith actors with no sense of humor downvote this valid starting point of discussion.