News for hackers. Stuff that matters.
Re:An OpenAI model has disproved a central conjecture in dis... by trostaft on Wednesday May 20, 2026 @05:08PM (#48214152)
Arguing similarly to how stockfish, the chess engine, trains I would not be surprised if this is more common in the future. I don't know if they use any proof verification tools during their reinforcement learning procedure right now, as far as I know they've been focusing more on COT based strategies (w/o Lean). But I'm hardly an LLM expert, I don't know.
Re:An OpenAI model has disproved a central conjecture in dis... by vatsachak on Wednesday May 20, 2026 @09:34PM (#48216726)
They most definitely threw in rl with formal verification somewhere between GPT 4 and now. The models are better at not hallucinating. I don't think their IMO team are only show ponies...