30 Oct 2025
35m
“Sonnet 4.5’s eval gaming seriously undermines alignment evals, and this seems caused by training on alignment evals” by Alexa Pan, ryan_greenblatt
LessWrong (30+ Karma)
Open in Podwise to generate AI notes
Sign in to process this episode and unlock summaries, transcripts, highlights and translations.
Shownotes are not generated by Podwise.