More RLVR. Give it verifiable problems, if it doesn't find a solution move on, if it does, use that as a reward signal.
Can’t this be extended quite far? Use a cerebras-served model, use verification techniques to generate and solve millions of problems and then use that as training?
alt Hacker News
Can’t this be extended quite far? Use a cerebras-served model, use verification techniques to generate and solve millions of problems and then use that as training?