New paradigm: instead of curating problems, create environments where models discover reasoning through competition.
Self-play = autonomous improvement without human supervision. Simple games improve general reasoning!
Bo Liu (Benjamin Liu)
@benjamin-eecs.bsky.social
122 followers 21 following 8 posts
Reinforcement Learning PhD @NUSingapore | Undergrad @PKU1898 | Building autonomous decision making systems | Ex intern @MSFTResearch @deepseek_ai | DeepSeek-V2, DeepSeek-VL, DeepSeek-Prover
