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

Deciphering AI Strategies

The chapter discusses the challenges of AI models proposing strategies without explanations, focusing on implications for decision-making and competitiveness. It explores training AI models to provide comprehensible rationale, referencing AlphaGo and AlphaFold. The conversation touches on safety measures, risks, and the need for coordination in preventing catastrophic outcomes.

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