Reasoning models don't always say what they think

Re:Reasoning models don't always say what they think by Workaccount2 on Thursday April 03, 2025 @11:47PM (#43578136)

Humans think they can produce chain-of-reasoing, but it has been shown many times (and is self evident if you pay attention) that your brain is making decisions before you are aware of it.

If I ask you to think of a movie, go ahead, think of one.....whatever movie just came into your mind was not picked by you, it was served up to you from an abyss.

[ Parent | on HN ]

Re:Reasoning models don't always say what they think by zja on Friday April 04, 2025 @01:14AM (#43578573)

How is that in conflict with the fact that humans can introspect?

[ Parent | on HN ]

Re:Reasoning models don't always say what they think by vidarh on Friday April 04, 2025 @06:03AM (#43580149)

Split brain experiments shows that human "introspection" is fundamentally unreliable. The brain is trivially coaxed into explaining how it made decisions it did not make.

We're doing the equivalent of LLM's and making up a plausible explanation for how we came to a conclusion, not reflecting reality.

[ Parent | on HN ]

Re:Reasoning models don't always say what they think by btilly on Friday April 04, 2025 @01:35PM (#43585523)

Ah yes. See https://en.wikipedia.org/wiki/Left-brain_interpreter for more about this.

As one neurologist put it, listening to people's explanations of how they think is entertaining, but not very informative. Virtually none of what people describe correlates in any way to what we actually know about how the brain is organized.

[ Parent | on HN ]