Rutherford and Fry on Living with AI: A Future for Humans
Curious Cases
Is That Enough?
We're just at the petty, exhilarating beginning of the process of actually building these systems that can learn general things from human preferences. A collaboration between deep mind in london and open a iye in san francisco set out to try to determine if they could get a robot to do a back flip. And so what the team did was they had this robot just wriggling around at random, and then it would show you two video is of different random writhing. Over the course of about one hour, the robot starts doing these kind of gymnastically perfect back flips. You know, i'm not naive about what it would take to scale up from back flips to, you know
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
