Live data from Hacker News

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

ml-site.cdn-apple.com

11–20 of 276 posts

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

#11

Earlier quoted context omitted.

Your god analogy is clumsy in this case. We aren't talking about something fantastical here. Reasoning is not difficult to define. We can go down that road if you'd like. Rather, the problem is, once you do define it, you will quickly find that LLMs are capable of it. And that makes human exceptionalists a bit uncomfortable.

"It's just statistics!", said the statistical-search survival-selected statistically-driven-learning biological Rube Goldberg contraption, between methane emissions. Imagining that a gradient learning algorithm, optimizing its statistical performance, is the same thing as only learning statistical relationships. Inconvertibly demonstrating a dramatic failure in its, and many of its kind's, ability to reason.

Reasoning exists on a spectrum, not as a binary property. I'm not claiming that LLMs reason identically to humans in all contexts.

You act as if statistical processes can’t ever scale into reasoning, despite the fact that humans themselves are gradient-trained statistical learners over evolutionary and developmental timescales.

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

#13

Earlier quoted context omitted.

Your god analogy is clumsy in this case. We aren't talking about something fantastical here. Reasoning is not difficult to define. We can go down that road if you'd like. Rather, the problem is, once you do define it, you will quickly find that LLMs are capable of it. And that makes human exceptionalists a bit uncomfortable.

Humans are exceptional though.

Oh my sweet summer child

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

#14

[flagged]

Your tone is a bit odd, but I agree with you on this 100%.

Without properly defining what thinking is and what is not, you can't discuss it's properties, let alone discuss which entity manifests it or not.

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

#15

Earlier quoted context omitted.

"It's just statistics!", said the statistical-search survival-selected statistically-driven-learning biological Rube Goldberg contraption, between methane emissions. Imagining that a gradient learning algorithm, optimizing its statistical performance, is the same thing as only learning statistical relationships. Inconvertibly demonstrating a dramatic failure in its, and many of its kind's, ability to reason.

Reasoning exists on a spectrum, not as a binary property. I'm not claiming that LLMs reason identically to humans in all contexts. You act as if statistical processes can’t ever scale into reasoning, despite the fact that humans themselves are gradient-trained statistical learners over evolutionary and developmental timescales.

I think you might re-read what I wrote.

I very strongly agree with you. :)

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

#16

[flagged]

Your tone is a bit odd, but I agree with you on this 100%. Without properly defining what thinking is and what is not, you can't discuss it's properties, let alone discuss which entity manifests it or not.

On the other hand: nobody can formally refute that a stone is reasoning/thinking.

Lack of definition seems to be ideal substrate for marketing and hype.

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

#18
post #4

Earlier quoted context omitted.

Equivalent: "I'm so sick of these [atheist] cretins proclaiming that [god doesn't exist], and when you drill down to first principles, these same people do not have a rigorous definition of [god] in the first place!" That's nonsense, because the people obligated to furnish a "rigorous definition" are the people who make the positive claim that something specific is happening. Also, the extraordinary claims are the on…

Your god analogy is clumsy in this case. We aren't talking about something fantastical here. Reasoning is not difficult to define. We can go down that road if you'd like. Rather, the problem is, once you do define it, you will quickly find that LLMs are capable of it. And that makes human exceptionalists a bit uncomfortable.

Hypothetically.

Imagine a simple, but humongous hash table, that maps every possible prompt of 20000 letters to the most appropriate answer in current time.

(How? Let’s say outsourcing to east asia or aliens…)

Would you say such mechanism is doing reasoning?

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

#19
I've seen this too often, papers that ask questions they don't even bother to properly define.

> Are these models capable of generalizable reasoning, or are they leveraging different forms of pattern matching?

Define reasoning, define generalizable, define pattern matching.

For additional credits after you have done so, show humans are capable of what you just defined as generalizable reasoning.

Post reply on HN