The TED Interview cover image

DeepMind's Demis Hassabis on the future of AI

The TED Interview

00:00

The Dope Mean Response to Reward in the External World

Alfa zero is a computer programme that can play chess against itself. It uses an adversarial model to train the system's predictive capability. Alfago and star croft are two other programmes based on this approach. The aim of all these programs is to teach people how to be more self-aware in real life.

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