Re:DeepSeek: Inference-Time Scaling for Generalist Reward Mo...
by NitpickLawyer on Friday April 04, 2025 @04:28PM
(#43587303)
> The idea of role-playing as different characters is novel.
It is not. I remember Karpathy being really excited about the "1 million gpt personas" dataset and highlighted it as a way to avoid reward hacking in RLAIF. That was 3-6 months ago I believe.
Of course paper / code / weights beats idea, and it's exciting to see how far this can go.
It is not. I remember Karpathy being really excited about the "1 million gpt personas" dataset and highlighted it as a way to avoid reward hacking in RLAIF. That was 3-6 months ago I believe.
Of course paper / code / weights beats idea, and it's exciting to see how far this can go.