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

Simple tasks showing reasoning breakdown in state-of-the-art LLMs

arxiv.org

Post reply on HN
Print view View original

331–340 of 393 posts

Re: Simple tasks showing reasoning breakdown in state-of-the-art LLMs

#331

Post by YeGoblynQueenne »

pretendscholar wrote: post #305
YeGoblynQueenne wrote: post #296

Earlier quoted context omitted.

That's a fascinating insight and it sound so true! Can you compress for me Van Gogh's Starry Night, please? I'd like to send a copy to my dear old mother who has never seen it. Please make sure when she decompresses the picture she misses none of the exquisite detail in that famous painting.

Okay yes so not really having an artists vocabulary I couldn't compress it as well as someone who has a better understanding of Starry Night. An artist that understands what makes Starry Night great could create a work that evokes similar feelings and emotions. I know this because Van Gogh created many similar works playing with the same techniques, colors, and subjects such as Cypresses in Starry Night and Starry Ni…

Fine, but we were talking about compression, not about imitation, or inspiration, and not about creating "a work that evokes similar feelings and emotions". If I compress an image, what I get when I decompress it is that image, not "feelings and emotions", yes? In fact, that's kind of the whole point: I can send an image over the web and the receiver can form their own feelings and emotions, without having to rely on mine.

Re: Simple tasks showing reasoning breakdown in state-of-the-art LLMs

#332

Post by solidasparagus »

Vegenoid wrote: post #328
solidasparagus wrote: post #302

Earlier quoted context omitted.

Fine, you can ignore my previous comment, that's just my answer to the question that this discussion ultimately takes you to. But I feel like you are just sitting on the sidelines making strawmen and playing pedantic games instead of saying anything constructive. The original comment said: > If you really think about what an LLM is you would think there is no way that leads to general purpose AI. This is an inflammat…

> I made no claims, I asked no one to prove anything wrong. Your original comment was: > It is an autoregressive sequence predictor/generator. Explain to me how humans are fundamentally different. Which would be interpreted by most reasonable people as you making the claim that humans are autoregressive sequence predictors, and asking people to prove you wrong. I can see how you could say this without intending to ma…

You're right, it was hastily written and I was annoyed.

But I generally hold out hope that people can see a claim "A!=B" and a response "A=C, explain how C!=B" and understand that is not the same as claiming "C=B", especially on HN.

Re: Simple tasks showing reasoning breakdown in state-of-the-art LLMs

#333

Post by hombre_fatal »

TeMPOraL wrote: post #306
hombre_fatal wrote: post #287

Earlier quoted context omitted.

Because we can't be sure whether two people interpret what "inner monologue" means and whether they think it describes a phenomenon that actually isn't different between them and other people. For example, I can think of interpretations of "I picture objects that I'm thinking about" that range from me not experiencing the phenomenon to me indeed experiencing the phenomenon. To say that you're not experiencing somethi…

And here I thought this was solved decades ago - I need to find the source, but I read about an old study where people describe their experience, and the answers were all over the "range from me not experiencing the phenomenon to me indeed experiencing the phenomenon". Then again, it's trivially reproducible - people self-report all variants of inner monologue, including lack of it, whenever a question about it pops…

I'm responding to "why can't we just take their word for it?"

That you and I can come up with different ways to describe our subjective experience in conversation doesn't mean that we have a different subjective experience.

Especially not when relayed by a species that's frequently convinced it has a trending mental disorder from TikTok.

Re: Simple tasks showing reasoning breakdown in state-of-the-art LLMs

#334

Post by nyrikki »

photon_lines wrote: post #160
throwanem wrote: post #147

Earlier quoted context omitted.

"Prove me wrong?" That's not how this works. Your implicit claim here is that human cognition and LLM functioning are fundamentally similar. That claim requires substantiation.

I actually did a full write-up on this here fyi: https://photonlines.substack.com/p/intuitive-and-visual-guid... . You can skip most of this and scroll down to the end-section called 'The Mental Model for Understanding LLMs' where I try to map how transformers are able to mimic human thinking. I think that comparing them to auto-associative / auto-regressive networks is actually a really good analogy FYI and I do bel…

Human neurons are continuous input, with active dendrites and dendritic compartmentalization. Spikey artificial NNs seem to hit problems with riddled basins so far. A riddled basin is a set with no open subsets.

Feed forward networks are effectively DAGs, and circuit like, not TM like.

Caution is warranted when comparing perceptrons with biological neurons.

Dendrites can perform XOR operations before anything makes it to the soma for another lens.

While there is much to learn, here is one highly cited paper on dendritic compartmentalization.

https://mcgovern.mit.edu/wp-content/uploads/2019/01/1-s2.0-S...

I think that the perceptron model of learning plasticity is on pretty shaky ground as being a primary learning model for humans.

Re: Simple tasks showing reasoning breakdown in state-of-the-art LLMs

#335

Post by tsunamifury »

elicksaur wrote: post #330
tsunamifury wrote: post #90

Earlier quoted context omitted.

Why are so many people so insistent on saying this? I’m guessing you are in denial that we can make a simulated reasoning machine?

Maybe people have different experiences with the products than you. A simulated reasoning machine being possible does not mean that current LLMs are simulated thinking machines. Maybe you should try asking chatgpt for advice on how to understand other people’s perspectives: https://chatgpt.com/share/3d63c646-859b-4903-897e-9a0cb7e47b...

This is such a weirdly preachy and belligerent take.

Obviously that was implied in my statement. Dude we aren’t all 4 year olds that need a self righteous lesson

Re: Simple tasks showing reasoning breakdown in state-of-the-art LLMs

#336

Post by TeMPOraL »

hombre_fatal wrote: post #333
TeMPOraL wrote: post #306

Earlier quoted context omitted.

And here I thought this was solved decades ago - I need to find the source, but I read about an old study where people describe their experience, and the answers were all over the "range from me not experiencing the phenomenon to me indeed experiencing the phenomenon". Then again, it's trivially reproducible - people self-report all variants of inner monologue, including lack of it, whenever a question about it pops…

I'm responding to "why can't we just take their word for it?" That you and I can come up with different ways to describe our subjective experience in conversation doesn't mean that we have a different subjective experience. Especially not when relayed by a species that's frequently convinced it has a trending mental disorder from TikTok.

We can keep talking about it, and assuming we're both honest, we'll arrive at the answer to whether or not our subjective experiences differ. To fail at that would require us to have so little in common that we wouldn't be able to communicate at all. Which is obviously not the case, neither for us, nor for almost every possible pair of humans currently alive.

Re: Simple tasks showing reasoning breakdown in state-of-the-art LLMs

#337

Post by tsunamifury »

YeGoblynQueenne wrote: post #331
pretendscholar wrote: post #305

Earlier quoted context omitted.

Okay yes so not really having an artists vocabulary I couldn't compress it as well as someone who has a better understanding of Starry Night. An artist that understands what makes Starry Night great could create a work that evokes similar feelings and emotions. I know this because Van Gogh created many similar works playing with the same techniques, colors, and subjects such as Cypresses in Starry Night and Starry Ni…

Fine, but we were talking about compression, not about imitation, or inspiration, and not about creating "a work that evokes similar feelings and emotions". If I compress an image, what I get when I decompress it is that image, not "feelings and emotions", yes? In fact, that's kind of the whole point: I can send an image over the web and the receiver can form their own feelings and emotions, without having to rely on…

Simple reasoning is a side effect of compression. That is all.

I see from your profile you are focused on your own personal and narrow definition of reasoning. But I’d argue there is a much broader and simpler definition. Can you summarize and apply learnings. This can.

Re: Simple tasks showing reasoning breakdown in state-of-the-art LLMs

#338

Post by throwanem »

solidasparagus wrote: post #332
Vegenoid wrote: post #328

Earlier quoted context omitted.

> I made no claims, I asked no one to prove anything wrong. Your original comment was: > It is an autoregressive sequence predictor/generator. Explain to me how humans are fundamentally different. Which would be interpreted by most reasonable people as you making the claim that humans are autoregressive sequence predictors, and asking people to prove you wrong. I can see how you could say this without intending to ma…

You're right, it was hastily written and I was annoyed. But I generally hold out hope that people can see a claim "A!=B" and a response "A=C, explain how C!=B" and understand that is not the same as claiming "C=B", especially on HN.

I do remain convinced my interpretation was sound, but on review I have to concede it was also quite uncharitable.

With all the wildly overheated claims that've been flying around since the advent of these models, I may be myself somewhat overfitted. Granted, in such an environment I feel like a little extra care for epistemic hygiene is warranted. But there was no reason for me to be rude about it.

Re: Simple tasks showing reasoning breakdown in state-of-the-art LLMs

#339

Post by Vegenoid »

solidasparagus wrote: post #332
Vegenoid wrote: post #328

Earlier quoted context omitted.

> I made no claims, I asked no one to prove anything wrong. Your original comment was: > It is an autoregressive sequence predictor/generator. Explain to me how humans are fundamentally different. Which would be interpreted by most reasonable people as you making the claim that humans are autoregressive sequence predictors, and asking people to prove you wrong. I can see how you could say this without intending to ma…

You're right, it was hastily written and I was annoyed. But I generally hold out hope that people can see a claim "A!=B" and a response "A=C, explain how C!=B" and understand that is not the same as claiming "C=B", especially on HN.

I know what you mean. Unfortunately, it's easy for frank and concise language to be taken the wrong way when in written form (and sometimes even verbal form). I wish I didn't have to make qualifiers about my intent on my internet comments, but I often do, to try and make sure that other people take my comment the way I intended it. I think it generally leads to better discussion.

I don't blame people for not wanting to talk this way.

Re: Simple tasks showing reasoning breakdown in state-of-the-art LLMs

#340

Post by tsunamifury »

TeMPOraL wrote: post #323
tsunamifury wrote: post #90

Earlier quoted context omitted.

Why are so many people so insistent on saying this? I’m guessing you are in denial that we can make a simulated reasoning machine?

There's some irony in seeing people parrot the argument that LLMs are parrots.

Also making errors in reasoning while saying LLM errors prove it can’t reason.
Post reply on HN