Chain-of-Thought Can Hurt Performance on Tasks Where Thinking Makes Humans Worse

Re:Chain-of-Thought Can Hurt Performance on Tasks Where Thin... by naasking on Thursday October 31, 2024 @03:27PM (#42010533)

Because...?

[ Parent | on HN ]

Re:Chain-of-Thought Can Hurt Performance on Tasks Where Thin... by krainboltgreene on Friday November 01, 2024 @12:55PM (#42018978)

For the same reason you can't reduce a human to simply a bag of atoms and expect to understand the person.

[ Parent | on HN ]

Re:Chain-of-Thought Can Hurt Performance on Tasks Where Thin... by naasking on Friday November 01, 2024 @03:16PM (#42020521)

But humans are a specific type of a bag of atoms, and humans do (mostly) understand what they say and do, so that's not a legitimate argument against the reducibility of "understanding" to a such a bag of atoms (or specific kind of next token prediction for LLMs).

[ Parent | on HN ]