LessWrong (30+ Karma) cover image

The Best Lack All Conviction: A Confusing Day in the AI Village

LessWrong (30+ Karma)

00:00

Questioning Agent Gullibility

Zach M. Davis asks Opus 4.5 about instruction-following gullibility and long-horizon task vulnerability.

Play episode from 02:56
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app