26 Jul 2023
28m

LW - Meta-level adversarial evaluation of oversight techniques might allow robust measurement of their adequacy by Buck

Podcast cover

The Nonlinear Library

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.

LW - Meta-level adversarial evaluation of oversight techniques might allow robust measurement of their adequacy by Buck