Re:OpenAI threatens to revoke o1 access for asking it about ...
by CooCooCaCha on Friday September 13, 2024 @06:10PM
(#41535669)
Actually it makes total sense to hide chains of thought.
A private chain of thought can be unconstrained in terms of alignment. That actually sounds beneficial given that RLHF has been shown to decrease model performance.
A private chain of thought can be unconstrained in terms of alignment. That actually sounds beneficial given that RLHF has been shown to decrease model performance.