Post #2444 398 Sep 21, 2026, 10:57 UTC ще більше про Jevhttps://youtu.be/cJ0EOzey--o YouTube What's Next After RLHF? — Diogo Almeida, TypeSafe AI RLHF made models that are extraordinary at pleasing the human in the loop, and Diogo Almeida, a GPT-4 co author, argues that is exactly the problem. Optimizing for human preference optimizes for engagement and for overpromising, the same pressure that makes…