AXRP - the AI X-risk Research Podcast cover image

1 - Adversarial Policies with Adam Gleave

AXRP - the AI X-risk Research Podcast

00:00

Kick and Defent

i wish we had much better machine learning interpret ability. This till be my best guess, but i don't think we have a great understanding of what's actually going on here yet. If the position of a kick is no limb predicts which direction it will go in then maybe an adversary al goly just really maks out this feature by putting its limb a weard position. It de stabilizes the control mechanism in vacecas.

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