News for hackers. Stuff that matters.

A comment on Orca: Progressive Learning from Complex Explanation Traces of GPT-4. Parent comment

Re:Orca: Progressive Learning from Complex Explanation Trace... by tehsauce on Tuesday June 13, 2023 @11:35AM (#36311804)
Nope! That surely doesn't apply to humans, why would it necessarily apply to learning machines?
[ Parent | on HN ]
Re:Orca: Progressive Learning from Complex Explanation Trace... by JoshuaDavid on Tuesday June 13, 2023 @08:51PM (#36319800)
The human equivalent would be the process of armchair philosophizing. Humans get around the limit by being able to go and look at the world to obtain more knowledge -- if you didn't let humans look at the world, they too would have a "knowledge limit".

And if you _do_ let LLMs look at the world, and train on that, they also wouldn't have that limitation.

[ Parent | on HN ]