The Inside View cover image

Tony Wang on Beating Superhuman Go AIs with Advesarial Policies

The Inside View

00:00

The Robustness of AI Systems

A team of computer scientists has created an AI system that can be used to attack other systems. The researchers say they don't know how strong it is, but their results suggest a human could still pull off the attack against defended systems. Their research was inspired by curiosity and long-term goals for building reliableAI systems. They also believe search alone isn't enough if you're not planning your actions properly.

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