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

Thomas Larsen's Background and Work in AI Safety

Thomas Larsen discusses his experience in technical AI safety, including his work on goal misgeneralization and techniques for mitigating it. He also mentions his theoretical conceptual work at Miri and his previous empirical ML research on out of distribution robustness at the University of Michigan.

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