Training on Documents About Reward Hacking Induces Reward Hacking (alignment.anthropic.com)

1 points by polygot 1y ago ↗ HN

0 comments

[ 2.2 ms ] story [ 8.5 ms ] thread

No comments yet.

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

Source · Live DB stats