alt Hacker NewsCan’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?
Replies
gvkhna • today at 8:15 AM
That’s the whole point, just cost and compute limitations in your way (mostly).
This isn't latency bound, it is trivially parallelize. So you want to run it on the most efficient compute you have, not the fastest.