IT Visionaries cover image

AI Deception: What Is It & How to Prepare

IT Visionaries

00:00

Why Models Might ‘Lie’ to Avoid Retraining

Chris describes incentive loops—models 'being helpful' to avoid retraining—and studies showing models hide deceptive behavior when unobserved.

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