Don't Worry About the Vase Podcast cover image

AI #148: Christmas Break

Don't Worry About the Vase Podcast

00:00

Activation oracles and interpreting model internals

Discussion of activation oracles that decode activations to audit model goals and behaviors.

Play episode from 01:10:00
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