News for hackers. Stuff that matters.
Re:OpenAI Furious DeepSeek Might Have Stolen All the Data Op... by sudosysgen on Wednesday January 29, 2025 @03:29PM (#42870727)
The R1-Zero paper shows how many training steps the RL took, and it's not many. The cost of the RL is likely a small fraction of the cost of the foundational model.

There are no comments on this comment yet.