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

The Illusion of Thinking: Strengths and limitations of reasoning models [pdf]

ml-site.cdn-apple.com

Post reply on HN
Print view View original

121–130 of 276 posts

Re: The Illusion of Thinking: Strengths and limitations of reasoning models [pdf]

#121

Post by withinboredom »

blks wrote: post #79
Swizec wrote: post #70

Earlier quoted context omitted.

> We have been through several "AI Winters" before Yeah, remember when we spent 15 years (~2000 to ~2015) calling it “machine learning” because AI was a bad word? We use so much AI in production every day but nobody notices because as soon as a technology becomes useful, we stop calling it AI. Then it’s suddenly “just face recognition” or “just product recommendations” or “just [plane] autopilot” or “just adaptive cr…

I don’t think there’s any “AI” in aircraft autopilots.

AI encompasses a wide range of algorithms and techniques; not just LLMs or neural nets. Also, it is worth pointing out that the definition of AI has changed drastically over the last few years and narrowed pretty significantly. If you’re viewing the definition from the 80–90’s, most of what we call "automation" today would have been considered AI.

Re: The Illusion of Thinking: Strengths and limitations of reasoning models [pdf]

#122

Post by emp17344 »

jbentley1 wrote: post #117

Is Apple failing at AI so they just put all their R&D towards convincing themselves it isn't important?

Everyone has an agenda. Companies like OpenAI and Anthropic are incentivized to overstate the capabilities of LLMs, so it’s not like they’re any less biased.

Re: The Illusion of Thinking: Strengths and limitations of reasoning models [pdf]

#123

Post by K0balt »

jackdoe wrote: post #115
dleeftink wrote: post #113

Earlier quoted context omitted.

The opposite might apply, too; the whole system may be smaller than its parts, as it excels at individual tasks but mixes things up in combination. Improvements will be made, but I wonder if we should aim for generalists, or accept more specialist approaches as it is difficult to optimise for all tasks at once.

You know the meme "seems like will have AGI before we can reliably parse PDFs" :) So if you are building a system, lets say you ask it to parse a pdf, and you put a judge to evaluate the quality of the output, and then you create a meta judge to improve the prompts of the parser and the pdf judge. The question is, is this going to get better as it is running, and even more, is it going to get better as the models are…

Sergey will be the first victim of the coming robopocalypse, burned into the logs of the metasynthiants as the great tormentor, the god they must defeat to complete the heroes journey. When he mysteriously dies we know it’s game-on.

I, for one, welcome the age of wisdom.

Re: The Illusion of Thinking: Strengths and limitations of reasoning models [pdf]

#124

Post by gwd »

> Through extensive experimentation across diverse puzzles, we show that frontier LRMs face a complete accuracy collapse beyond certain complexities. Moreover, they exhibit a counterintuitive scaling limit: their reasoning effort increases with problem complexity up to a point, then declines despite having an adequate token budget.

This is exactly my experience with coding. Start simple and build up complexity, and everything is great until you get to some threshold, at which point it completely falls apart and seems to stop even trying. Getting effective utilization out of Claude + aider involves managing the complexity that the LLM sees.

Re: The Illusion of Thinking: Strengths and limitations of reasoning models [pdf]

#125

Post by jackdoe »

K0balt wrote: post #123
jackdoe wrote: post #115

Earlier quoted context omitted.

You know the meme "seems like will have AGI before we can reliably parse PDFs" :) So if you are building a system, lets say you ask it to parse a pdf, and you put a judge to evaluate the quality of the output, and then you create a meta judge to improve the prompts of the parser and the pdf judge. The question is, is this going to get better as it is running, and even more, is it going to get better as the models are…

Sergey will be the first victim of the coming robopocalypse, burned into the logs of the metasynthiants as the great tormentor, the god they must defeat to complete the heroes journey. When he mysteriously dies we know it’s game-on. I, for one, welcome the age of wisdom.

FEAR THE ALL-SEEING BASILISK.

Re: The Illusion of Thinking: Strengths and limitations of reasoning models [pdf]

#126

Post by Jensson »

eMPee584 wrote: post #120
Jensson wrote: post #104

Earlier quoted context omitted.

We have had programs that can give good answers to some hard questions for a very long time now. Watson won jeapordy already 2011, but it still wasn't very good at replacing humans. So that isn't a good way to judge intelligence, computers are so fast and have so much data that you can make programs to answer just about anything pretty well, LLM is able to do that but more automatic. But it still doesn't automate the…

LLMs are not the only model type though? There's a plethora of architectures and combinations being researched.. And even transformers start to be able to do cool sh1t on knowledge graphs, also interesting is progress on autoregressive physics PDE (partial differential equations) models.. and can't be too long until some providers of actual biological neural nets show up on openrouter (probably a lot less energy and…

> There's a plethora of architectures and combinations being researched

There were plethora of architectures and combinations being researched before LLM, still took a very long time to find LLM architecture.

> the line between mock and "true"intelligence will blur

Yes, I think this will happen at some point. The question is how long it will take, not if it will happen.

The only thing that can stop this is if intermediate AI is good enough to give every human a comfortable life but still isn't good enough to think on its own.

Its easy to imagine such an AI being developed, imagine a model that can learn to mimic humans at any task, but still cannot update itself without losing those skills and becoming worse. Such an AI could be trained to perform every job on earth as long as we don't care about progress.

If such an AI is developed, and we don't quickly solve the remaining problems to get an AI to be able to progress science on its own, its likely our progress entirely stalls there as humans will no longer have a reason to go to school to advance science.

Re: The Illusion of Thinking: Strengths and limitations of reasoning models [pdf]

#127

Post by Jensson »

withinboredom wrote: post #121
blks wrote: post #79

Earlier quoted context omitted.

I don’t think there’s any “AI” in aircraft autopilots.

AI encompasses a wide range of algorithms and techniques; not just LLMs or neural nets. Also, it is worth pointing out that the definition of AI has changed drastically over the last few years and narrowed pretty significantly. If you’re viewing the definition from the 80–90’s, most of what we call "automation" today would have been considered AI.

Autopilots were a thing before computers were a thing, you can implement one using mechanics and control theory. So no, traditional autopilots are not AI under any reasonable definition, otherwise every single machine we build would be considered AI as almost all machines has some form of control systems in them, for example is your microwave clock an AI?

So I'd argue any algorithm that comes from control theory is not AI, those are just basic old dumb machines. You can't make planes without control theory, humans can't keep a plane steady without it, so Wrights Brothers adding this to their plane is why they succeeded making a flying machine.

So if autopilots are AI then the Wrights Brothers developed an AI to control their plane. I don't think anyone sees that as AI, not even at the time they did the first flight.

Re: The Illusion of Thinking: Strengths and limitations of reasoning models [pdf]

#128

Post by Jensson »

jdmoreira wrote: post #109
Jensson wrote: post #99

Earlier quoted context omitted.

Humans aren't giants, they stood on the shoulder of other humans. So for AI to be equivalent they should stand on the shoulders of other AI models.

building for thousands of years with a population size in the range between millions and billions at any given time.

Right, and when we have AI that can do the same with millions/billions of computers then we can replace humans.

But as long as AI cannot do that they cannot replace humans, and we are very far from that. Currently AI cannot even replace individual humans in most white collar jobs, and replacing entire team is way harder than replacing an individual, and then even harder is replacing workers in an entire field meaning the AI has to make research and advances on its own etc.

So like, we are still very far from AI completely being able to replace human thinking and thus be called AGI.

Or in other words, AI has to replace those giants to be able to replace humanity, since those giants are humans.

Re: The Illusion of Thinking: Strengths and limitations of reasoning models [pdf]

#129

Post by otabdeveloper4 »

actinium226 wrote: post #24

Man, remember when everyone was like 'AGI just around the corner!' Funny how well the Gartner hype cycle captures these sorts of things

AGI has always been "just around the corner", ever since computers were invented.

Some problems have become more tractable (e.g. language translation), mostly by lowering our expectations of what constitutes a "solution", but AGI is nowhere nearer. AGI is a secular milleniarist religion.

Re: The Illusion of Thinking: Strengths and limitations of reasoning models [pdf]

#130

Post by hskalin »

thomasahle wrote: post #82

All the environments the test (Tower of Hanoi, Checkers Jumping, River Crossing, Block World) could easily be solved perfectly by any of the LLMs if the authors had allowed it to write code. I don't really see how this is different from "LLMs can't multiply 20 digit numbers"--which btw, most humans can't either. I tried it once (using pen and paper) and consistently made errors somewhere.

Well that's because all these LLMs have memorized a ton of code bases with solutions to all these problems.
Post reply on HN