"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis cover image

AI Control: Using Untrusted Systems Safely with Buck Shlegeris of Redwood Research, from the 80,000 Hours Podcast

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis

00:00

Navigating AI Oversight Challenges

This chapter explores the complexities of monitoring advanced AI systems, emphasizing the difficulties in ensuring human oversight amid rapid AI decision-making. It discusses various strategies for evaluating AI behavior, particularly in identifying suspicious actions and their implications for safety and risk management. The conversation also highlights the balance between performance and safety, introducing control techniques to mitigate risks posed by potentially harmful AI actions.

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