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 There a Reliability of the Feedback Mechanism?

i think e i would view development of fields as often being quite half dependent. I don't really feel like i've got a comparative advantage in tat space, but if i did, i'd be reasonably excited about it. A lot of a problem isn't specific to deep networks. It's a more of a question of what when you have generally a powerful function? Approximatea a, you're using self play. You don't have adequate coverage. And i don't really see these fundamental problems as disappearing, unfortunately.

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