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 Safe to Say That You're Interested in Ai Alignment?

Multi agent or el is going to be the future in which most of our systems are going to be deployed. And now you don't necessarily have to do multi agent or el for everything like it. If you're just trained to train a autonomous spheicl, maybe it's enough to kind of ignore fother vehicles,. Not explicitly modeled for ma's agents, just modeld them as obstacles. Might sabs to do reasonably well in some cases.

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