Weak-to-Strong Generalization

Re:Weak-to-Strong Generalization by lossolo on Thursday December 14, 2023 @05:13PM (#38648065)

> Is this worse than every human that can take these tests. Is this even worse than most ? I can tell you it's not. So again, why is GPT-4 not agi ?

[ Parent | on HN ]

Re:Weak-to-Strong Generalization by og_kalu on Thursday December 14, 2023 @05:43PM (#38648417)

Love it when people can only demonstrate tasks handicapped by Tokenization. Shows how far we've come.

That said, By that test, I guess some dyslexics aren't general intelligences then.

[ Parent | on HN ]

Re:Weak-to-Strong Generalization by lossolo on Thursday December 14, 2023 @05:59PM (#38648587)

Tokenization is not the problem in this case.

You see the difference?

[ Parent | on HN ]