at2005
Joined 6 years ago
Karma
68
Submissions
6
Member since
Jun 21
https://ayushtambde.com/
View on Hacker NewsRecent submissions
Comment · 7 months ago
I didn't compare with the harness (focused on distillation) but the original ToT paper has a section on it: https://arxiv.org/abs/2305.10601
Comment · 7 months ago
Ah, I meant that MCTS uses more inference-time compute (over GRPO) to produce a training sample
Comment · 5 years ago
Btw the whole motivation for this were algorithms like Grover's, which need "oracles" to be specified. You can only imagine trying to code adders and greater-than circuits with QASM...