Making Sense with Sam Harris - Subscriber Content cover image

#312 - The Trouble with AI

Making Sense with Sam Harris - Subscriber Content

00:00

How to Lock Down Core Values in Machine Learning

Is it possible to lock down core values? Are those core values sufficient to prevent the kinds of, you know, optimizations that we don't want where we get turned into paperclips? The paperclip example itself always seems silly to me because it seems like, well, why can't you just represent explicitly the value of human life? And then if you do, then that one just gets ruled out as being at odds with the axiom. It's really a question about inateness and values and whether we can do that.

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