Future of Life Institute Podcast cover image

Connor Leahy on AGI and Cognitive Emulation

Future of Life Institute Podcast

00:00

How to Build a Powerful Safe System

The more powerful a system is, the stronger its safety guarantees have to be. Connor: There's an important difference here between the specification and the boundedness of AI. He says there are two types of boundedness - in the specification level and at the hardware level. "If you can build a thing that actually fulfills the specifications?" he asks.

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