The Art of Scaling Reinforcement Learning Compute for LLMs [Meta] (arxiv.org)

1 points by wavelander 11mo ago ↗ HN

0 comments

[ 3.5 ms ] story [ 11.2 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats