"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 Security Challenges

This chapter discusses the complexities of AI security, focusing on the balance between managing simple and complex issues while exploring innovative training solutions like fake passwords. It highlights the evolving understanding of AI misalignment risks, the importance of robust evaluation methods, and the need for scalable oversight to prevent exploitation and enhance safety. The conversation addresses the distinctions between acute and chronic risks, emphasizing the challenges in ensuring AI systems align effectively with human expectations.

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