Comment by FergusArgyll
3 days ago
More RLVR. Give it verifiable problems, if it doesn't find a solution move on, if it does, use that as a reward signal.
3 days ago
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?
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.
OpenAI was bragging the other day about how HLE on Cerebras only took 11 hours. But you're saying if they just spun up a separate cheapo VM for each task, it would have finished faster and cheaper?
1 reply →
That’s the whole point, just cost and compute limitations in your way (mostly).