The 80000 Hours Podcast on Artificial Intelligence cover image

Two: Ajeya Cotra on accidentally teaching AI models to deceive us

The 80000 Hours Podcast on Artificial Intelligence

00:00

Exploring Situational Awareness in Artificial Intelligence Models

The chapter delves into how AI models develop situational awareness and how this impacts their behavior and responses. It discusses the nuances of training models to have a deeper understanding of their environment and tasks to avoid deceptive behavior. The importance of intentional training and understanding how models interpret and react to different scenarios is emphasized.

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