Prompt optimization can outperform reinforcement learning on LLMs (sderosiaux.substack.com)

1 points by chtefi 6mo ago ↗ HN

0 comments

[ 3.7 ms ] story [ 440 ms ] thread

No comments yet.

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

Source · Live DB stats