News for hackers. Stuff that matters.

A comment on GPT-4 performs better at Theory of Mind tests than actual humans. Parent comment

Re:GPT-4 performs better at Theory of Mind tests than actual... by seydor on Sunday April 30, 2023 @07:32PM (#35767534)
it is important in order for us to accept it as an agent that understands things, because self-reflection is so important and obvious to us.
[ Parent | on HN ]
Re:GPT-4 performs better at Theory of Mind tests than actual... by timschmidt on Sunday April 30, 2023 @07:55PM (#35767665)
I'm still waiting for someone to prove beyond a shadow of doubt that humans have a single one of these features we're debating about the presence or absence of in LLMs.
[ Parent | on HN ]
Re:GPT-4 performs better at Theory of Mind tests than actual... by seydor on Monday May 01, 2023 @02:29AM (#35769660)
there is no way to prove because those are subjective to humans. LLMs would have to at least show they have a subjective view (currently the 'internal world' they report is inconsistent)
[ Parent | on HN ]
Re:GPT-4 performs better at Theory of Mind tests than actual... by timschmidt on Monday May 01, 2023 @04:57AM (#35770494)
The internal worlds of humans are inconsistent: https://en.wikipedia.org/wiki/Shadow_(psychology)
[ Parent | on HN ]