AI Safety Fundamentals cover image

Introduction to AI Control

AI Safety Fundamentals

00:00

Specific Failure Modes and Research Needs

The host lists potential failure modes like collusion and sandbagging and calls for more empirical testing of controls.

Play episode from 09:37
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