Comment by stymaar
4 days ago
Yup, it varies between runs (depending on the seed, most likely), but since the knowledge is here it wouldn't be too hard to nudge the model in the right direction with grpo alone.
4 days ago
Yup, it varies between runs (depending on the seed, most likely), but since the knowledge is here it wouldn't be too hard to nudge the model in the right direction with grpo alone.
No comments yet
Contribute on Hacker News ↗