
Dylan Hadfield-Menell, UC Berkeley/MIT: The value alignment problem in AI
Generally Intelligent
00:00
Introduction
Josh albrecht is the head of untitled ai, an independent research lab that's investigating the fundamentals of learning across both humans and machines. We hope this ultimately becomes a sort of loba colloquium where we can get inspiration from each other in order to create more general machine intelligence. This is generally intelligent, a series of conversations with deep learning researchers about their behind the scenes ideas, opinions and intuitions that they normally wouldn't have the space to share in a typical paper or talk. And i think most of my research s about trying to understand, what are the channels by which we communicate that information.
Play episode from 00:00
Transcript


