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

191–200 of 276 posts

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

#191

Post by fc417fc802 »

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.

Ah yes the mythical strawman definition of AI that you can never seem to pin down, was never rigorous, and never enjoyed wide expert acceptance. It's on par with "well many people used to say, or at least so I've been told, that ...".

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

#192

Post by fc417fc802 »

trc001 wrote: post #137
Jensson wrote: post #127

Earlier quoted context omitted.

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 n…

Uh, the bellman equation was first used for control theory and is the foundation of modern reinforcement learning... so wouldn't that imply LLMs "come from" control theory?

Is the training algorithm the AI or is the model that you get at the end the AI?

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

#193

Post by ksec »

This actually set back my expectation of AI / LLM / LRM by at least 5 if not 10 years. But someone please correct me if I am wrong.

My idea was that up to a few years ago while AI / LLM is good at getting conversational or dishing out results that is in a language we understand. It still doesn't "understand" anything and in a lot of time conjured up that seems remotely correctly. Pattern matching over a very large data set that could be correct for 70% and increasingly to 80%+ of the time. However more accurate predictions would require order of magnitude more computing resources.

But pattern matching is still, pattern matching. There is no reasoning behind it. 1+1 will never equals to 11 but it may have skewed towards that results because of Javascript. When fundamental logic isn't behind any of these progress and process. The very bottom layer of any conversation / information / results are fragile.

So I have been skeptical of AI progress or LLM. That was until LRM or as the title said Reasoning LLMs. I thought we somehow manage to programme critical thinking into it, or some sort of reflection / fact checking / rationale / basic logic as fundamental principle. And while I can tell LRM isn't and wont be perfect, and possibly never quite reach AGI, the layer will improve over time until we find different ways to progress. And we will have something I called Assisted Intelligence. Which is what a lot of people uses as AI programming today.

Instead what this shows is that LRM isn't reasoning at all. It is LLM conjured up excuses to make it look like it is reasoning. It is another set of pattern matching specially made up for reasoning to look like it is reasoning. It is basically a kid making things up on why he got the results without thinking because he just want to get away from class or homework that looks very clever.

May be the title gave it away, and made be we got tricked. It was always a LLM specifically trained for showcasing "reasoning". The actual reasoning behind the scene is never done. Hence the title "The Illusion of Thinking".

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

#194

Post by pcooperchi »

thomasahle wrote: post #184
mjburgess wrote: post #148

Earlier quoted context omitted.

The goal isnt to assess the LLM capability at solving any of those problems. The point isnt how good they are at block world puzzles. The point is to construct non-circular ways of quantifying model performance in reasoning. That the LLM has access to prior exemplars of any given problem is exactly the issue in establishing performance in reasoning, over historical synthesis.

How are these problems more interesting than simple arithmetic or algorithmic problems?

The problems themselves aren’t particularly interesting, I suppose. The interesting part is how the complexity of each problem scales as a function of the number of inputs (e.g. the number of disks in the tower of Hanoi).

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

#195

Post by throw310822 »

moralestapia wrote: post #185
thomasahle wrote: post #90

Earlier quoted context omitted.

Some specialized people could probably do 20x20, but I'd still expect them to make a mistake at 100x100. The level we needed for space crafts was much less than that, and we had many levels of checks to help catch errors afterwards. I'd wager that 95% of humans wouldn't be able to do 10x10 multiplication without errors, even if we paid them $100 to get it right. There's a reason we had to invent lots of machines to h…

I don't think you got @Jensson's point. With enough effort and time we can arrive at a perfect solution to those problems without a computer. This is not a hypothetical, it was like that for at least hundreds of years.

With enough time and effort you can build an entire science of how arbitrarily complex computations can be done with pen and paper without errors in an arbitrarily long amount of time.

But then you're not measuring the ability to perform the calculations, but the ability to invent the methods that make the calculation possible.

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

#196

Post by tim333 »

Jensson wrote: post #126
eMPee584 wrote: post #120

Earlier quoted context omitted.

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 interme…

>The only thing that can stop this is if intermediate AI is good enough...

Not going to happen due to competition. As soon as one company has a good one their rivals will develop a better one.

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

#197

Post by empiricus »

mrbungie wrote: post #181
mirekrusin wrote: post #156

Earlier quoted context omitted.

I'm not sure if system capable of ie. reasoning over images deserves this label anymore?

The thing is "spicy" or "glorified" autocomplete are not actually bad labels, they are autocomplete machines that are very good up to the point of convincing people that they think.

Many ppl are good at convincing other ppl that they think, but also many fail at thinking and many fail at convincing.

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

#198

Post by tim333 »

BriggyDwiggs42 wrote: post #135
imiric wrote: post #92

Earlier quoted context omitted.

> I figure it's hard to argue that that is not at least somewhat intelligent? The fact that this technology can be very useful doesn't imply that it's intelligent. My argument is about the language used to describe it, not about its abilities. The breakthroughs we've had is because there is a lot of utility from finding patterns in data which humans aren't very good at. Many of our problems can be boiled down to this…

This approach to defining “true” intelligence seems flawed to me because of examples in biology where semantic understanding is in no way relevant to function. A slime mold solving a maze doesn’t even have a brain, yet it solves a problem to get food. There’s no knowing that it does that, no complex signal processing, no self-perception of purpose, but nevertheless it gets the food it needs. My response to that isn’t…

>LLMs lack anything in any way resembling human intelligence

I think intelligence has many aspects from moulds solving mazes to chess etc. I find LLMs resemble very much human rapid language responses where you say something without thinking about it first. They are not very good at thinking though. And hopeless if you were to say hook one to a robot and tell it to fix your plumbing.

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

#199

Post by anonzzzies »

bayindirh wrote: post #93
nmca wrote: post #77

Earlier quoted context omitted.

I saw your comment and counted — in May I took a Waymo thirty times.

Waymo is a popular argument in self-driving cars, and they do well. However, Waymo is Deep Blue of self-driving cars. Doing very well in a closed space . As a result of this geofencing, they have effectively exhausted their search space, hence they work well as a consequence of lack of surprises. AI works well when search space is limited, but General AI in any category needs to handle a vastly larger search space, a…

Yeah, AI has been good for a long time in limited search space areas. So good that many of these things that were called AI in the past are not called AI now, but 'just' 'algorithm'.

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

#200

Post by anonzzzies »

sneak wrote: post #43
yahoozoo wrote: post #30

Earlier quoted context omitted.

We will be treating LLMs “like a junior developer” forever.

Even if they never get better than they are today (unlikely) they are still the biggest change in software development and the software development industry in my 28 year career.

That's for sure; I said with the original chatgpt already ; if this is the level it stays at but just becomes (much) faster and open, it's already a bizar revolution. Something many old former (and current, as I see online, but I don't know any personally) AI students/researchers did not think possible in our lifetime, and there it was.
Post reply on HN