Press Space to continue
Safer AI Through Uncertainty About Human Intent
Press Space to continue
What if safer AI needs to be less certain about what you want? “There’s a third option, which is uncertain about what the human objective is,” says UC Berkeley AI professor Stuart Russell. On AI Deep Dive, he explains how that uncertainty could help humans retain control. 🚀 Watch the full episode of AI Deep Dive: https://youtube.com/watch?v=jiXeRe567CI
open on x · 2 viewsViews and clicks count once per visitor per day. Clicks are opens of this post on X.