AXRP - the AI X-risk Research Podcast cover image

1 - Adversarial Policies with Adam Gleave

AXRP - the AI X-risk Research Podcast

00:00

Is It Like a Rule of Fum in a Training Setting?

Deep learning is a new way of teaching computers how to learn. The technology has been developed by Google and the University of California, San Francisco. It's designed to be more robust than traditional computer programs that have had millions of training steps. But it can still make mistakes when playing against an adversary.

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