AI Safety Fundamentals cover image

Emergent Deception and Emergent Optimization

AI Safety Fundamentals

00:00

Emergent Behavior and External Reasoning

This chapter explores emergent behavior in AI models, including the concept of emergent deception and the effectiveness of chain of thought reasoning. It discusses the limitations of certain models and the role of in-context learning in decreasing training loss.

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