Artificial General Intelligence (AGI) Show with Soroush Pour cover image

Ep 11 - Technical alignment overview w/ Thomas Larsen (Director of Strategy, Center for AI Policy)

Artificial General Intelligence (AGI) Show with Soroush Pour

00:00

Exploring Interpretability and the Colin Burns Activation Probes Technique

Exploring the concept of interpretability in AI models and the Colin Burns activation probes technique, which identifies clusters that represent truthful and incorrect statements. The aim is to use this technique to enhance the truthfulness of AI models.

Transcript
Play full episode

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