Episode description
Geoff discusses Alpha Zero, a neural net that can play Go, Chess, and Shogi better than anyone in the world. It defeated the best AI in those respective games (each of whom had previously defeated the best humans in the world) with only a few hours of training. What does this spell for the future of AI, and the future of game design?
For the best experience, listen in Metacast app for iOS or Android
Open in Metacast