Chain-of-Thought Reasoning Is a Policy Improvement Operator (arxiv.org)

2 points by hughzhang 2y ago ↗ HN

0 comments

[ 3.7 ms ] story [ 8.4 ms ] thread

No comments yet.

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

Source · Live DB stats