Core Memory  cover image

OpenAI's Research Chief On The Soup Wars, Poker And The Next Models - EP 46 Mark Chen

Core Memory

00:00

Safety, alignment and mechanistic interpretability

Mark stresses alignment research, risks like scheming, and methods to observe model thinking without supervising it.

Play episode from 01:24:11
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