FUTURATI PODCAST cover image

Ep. 129: Applying the 'security mindset' to AI and x-risk | Jeffrey Ladish

FUTURATI PODCAST

00:00

The Importance of Interpretability in the Evolution of Agency

We don't know what these systems are capable of, and everyone everywhere is just stomping on the gas as quickly as they can. We have no principal reason for ruling out agency evolving in them. And we wouldn't necessarily know what it would look like if we were three tenths of the way there. I very much hope that that field receives a huge boost because we just don't have what we need to inspect the way these systems are evolving.

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