21 Jan 2025
4m

“Training on Documents About Reward Hacking Induces Reward Hacking” by evhub

Podcast cover

LessWrong (30+ Karma)

Open in Podwise to generate AI notes

Sign in to process this episode and unlock summaries, transcripts, highlights and translations.

Open in Podwise

Shownotes are not generated by Podwise.

“Training on Documents About Reward Hacking Induces Reward Hacking” by evhub