GPT-4 co-author Diogo Almeida on what's next after RLHF

Diogo Almeida, a GPT-4 co-author now at TypeSafe AI, argues RLHF is flawed because optimizing for human preference rewards engagement and overpromising, making models confidently agree with the user. He discusses what might replace it in an AI Engineer interview.

Featured · Diogo Almeida