Google DeepMind: The Podcast cover image

AI, Robot

Google DeepMind: The Podcast

00:00

Retinancing the a I

A team of researchers created an agent inside a very simple two dimensional computer game and tasked it with building itself a body. It worked out that it could just build itself taller and taller and taller until it was as high as the track was long, then just flop forwards to cross the line. There were plenty of examples like this. But there is a balancing act here. We don't want our a i misbehaving, but we also don't want to restrict agents too much.

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