Reasoning models reason well, until they don't • Hacker News Board

Re: Reasoning models reason well, until they don't

#111

Post by pfortuny » Fri, Oct 31, 2025, 1:05 PM UTC

PxldLtd wrote: post #57

My_Name wrote: post #45

I find that they know what they know fairly well, but if you move beyond that, into what can be reasoned from what they know, they have a profound lack of ability to do that. They are good at repeating their training data, not thinking about it. The problem, I find, is that they then don't stop, or say they don't know (unless explicitly prompted to do so) they just make stuff up and express it with just as much confi…

I think a good test of this seems to be to provide an image and get the model to predict what will happen next/if x occurs. They fail spectacularly at Rube-Goldberg machines. I think developing some sort of dedicated prediction model would help massively in extrapolating data. The human subconscious is filled with all sorts of parabolic prediction, gravity, momentum and various other fast-thinking paths that embed th…

Most amazing is asking any of the models to draw an 11-sided polygon and number the edges.

Re: Reasoning models reason well, until they don't

#112

Post by hirako2000 » Fri, Oct 31, 2025, 1:09 PM UTC

tempfile wrote: post #96

hirako2000 wrote: post #51

Has any one ever found an ML/AI paper that make claims that RLMs can reason? When I prompt an RLM, I can see it spits out reasoning steps. But I don't find that evidence RLMs are capable of reasoning.

I don't understand what point you are making. Doesn't the name "Reasoning language models" claim that they can reason? Why do you want to see it explicitly written down in a paper?

This very paper sits on the assumption reasoning (to solve puzzles) is at play. It calls those LLMs RLMs.

Imo the paper itself should have touched on the lack of paper discussing what's in the blackbox that makes them Reasoning LMs. It does mention some tree algorithm supposedly key to reasoning capabilities.

By no means attacking the paper as its intent is to demonstrate the lack of success to even solve simple to formulate, complex puzzles.

I was not making a point, I was genuinely asking in case someone knows of papers I could read on that make claims with evidence that's those RLM actually reason, and how.

Re: Reasoning models reason well, until they don't

#113

Post by Der_Einzige » Fri, Oct 31, 2025, 1:10 PM UTC

layer8 wrote: post #85

anal_reactor wrote: post #39

I'm yet to see a task that AI fails at that bottom 10% of population wouldn't also fail at.

If I have the choice of performing an intellectual task myself, or have it performed by someone from the bottom 10% of the population, I’d probably rather perform it myself.

What happens when both choices lead to you doing it yourself?

Re: Reasoning models reason well, until they don't

#114

Post by darkwater » Fri, Oct 31, 2025, 1:12 PM UTC

squidbeak wrote: post #83

flavaflav2 wrote: post #76

Earlier quoted context omitted.

Life and a lot in our universe is non-deterministic. Some people assume science and mathematics are some universal truths rather than imperfect agreed upon understandings. Similarly many assume humans can be controlled through laws, penalties, prisons, propaganda, coercion, etc. But terrible things happen. Yes, if you set up the gutter-rails in your bowling lane, you can control the bowling ball unless it is thrown o…

No, Science is a means of searching for those truths - definitely not some 'agreed upon understanding'. It's backed up by experimentation and reproducible proofs. You also make a huge bogus leap from science to humanities.

But those are still approximations to the actual underlying reality. Because the other option (and yes, it's a dichotomy) is that we already defined and understood every detail of the physics that applies to our universe.

Re: Reasoning models reason well, until they don't

#115

Post by darkwater » Fri, Oct 31, 2025, 1:14 PM UTC

pimeys wrote: post #91

My_Name wrote: post #45

I find that they know what they know fairly well, but if you move beyond that, into what can be reasoned from what they know, they have a profound lack of ability to do that. They are good at repeating their training data, not thinking about it. The problem, I find, is that they then don't stop, or say they don't know (unless explicitly prompted to do so) they just make stuff up and express it with just as much confi…

I just got this from codex yesterday: "I wasn’t able to finish; no changes were shipped." And it's not the first time.

Have you threatened it with a 2 in the next round of performance reviews?

Re: Reasoning models reason well, until they don't

#116

Post by riskable » Fri, Oct 31, 2025, 1:16 PM UTC

My hypothesis: This is why AI is fantastic as a coding assistant but not so great at other things. A software developer—after watching an AI model fail over and over again, trying to say, fix a difficult bug—will stop and approach the issue from a different angle. They'll take a closer look at what's going on, fiddle things around by hand, and that's usually enough to get over that hump of complexity (that the AI model couldn't work its way through).

We (developers) do this because it's what we've always done with our own code. Everyone's encountered a bug that they just couldn't figure out. So they search the Internet, try different implementations of the same thing, etc but nothing works. Usually, we finally solve such problems when we take a step back and look at it with a different lens.

For example, just the other day—after spending far too long trying to get something working—I realized, "Fuck it! The users don't really need this feature." :thumbsup:

Re: Reasoning models reason well, until they don't

#117

Post by hirako2000 » Fri, Oct 31, 2025, 1:17 PM UTC

Sharlin wrote: post #63

hirako2000 wrote: post #51

Has any one ever found an ML/AI paper that make claims that RLMs can reason? When I prompt an RLM, I can see it spits out reasoning steps. But I don't find that evidence RLMs are capable of reasoning.

Semantics schemantics.

It's a statistical imitation of a reasoning pattern, underlying mechanism is pattern matching. The ability to create a model that can determine two radically different words have strong similarity in meaning doesn't imply emergence of some generalizable, logical model that suddenly can Reason to solve novel problems.

Pattern matching is a component of reason. Not === reason.

Re: Reasoning models reason well, until they don't

#118

Post by Torkel » Fri, Oct 31, 2025, 1:21 PM UTC

pfortuny wrote: post #111

PxldLtd wrote: post #57

Earlier quoted context omitted.

I think a good test of this seems to be to provide an image and get the model to predict what will happen next/if x occurs. They fail spectacularly at Rube-Goldberg machines. I think developing some sort of dedicated prediction model would help massively in extrapolating data. The human subconscious is filled with all sorts of parabolic prediction, gravity, momentum and various other fast-thinking paths that embed th…

Most amazing is asking any of the models to draw an 11-sided polygon and number the edges.

I asked gpt5, and it worked really well with a correct result. Did you expect it to fail?

Re: Reasoning models reason well, until they don't

#119

Post by squidbeak » Fri, Oct 31, 2025, 1:21 PM UTC

darkwater wrote: post #114

squidbeak wrote: post #83

Earlier quoted context omitted.

No, Science is a means of searching for those truths - definitely not some 'agreed upon understanding'. It's backed up by experimentation and reproducible proofs. You also make a huge bogus leap from science to humanities.

But those are still approximations to the actual underlying reality. Because the other option (and yes, it's a dichotomy) is that we already defined and understood every detail of the physics that applies to our universe.

Indeed, that is a dichotomy: a false one. Science is exact without being finished.

Re: Reasoning models reason well, until they don't

#120

Post by squidbeak » Fri, Oct 31, 2025, 1:23 PM UTC

iq176 wrote: post #98

squidbeak wrote: post #83

Earlier quoted context omitted.

No, Science is a means of searching for those truths - definitely not some 'agreed upon understanding'. It's backed up by experimentation and reproducible proofs. You also make a huge bogus leap from science to humanities.

Scientific method is the process. Science itself includes the study and compendium of understandings, based on a belief system that includes shared understandings just like mathematics. The foundation of these are philosophical beliefs that we can know and understand these things. For example, on a metaphysical level, if the world around us were a simulation, then science could provide understandings about that simul…

This I'm afraid is rubbish. Scientific proofs categorically don't depend on philosophical beliefs. Reality is measurable and the properties measured don't care about philosophy.