Making Sense with Sam Harris - Subscriber Content cover image

Making Sense of Artificial Intelligence

Making Sense with Sam Harris - Subscriber Content

CHAPTER

Turing's Warning About the Value Alignment Problem

Turing was concerned because he saw Arthur Samuel's Checker playing program in 1959, learning to play checkers by itself. Wiener said if we are used to achieve our purposes, a mechanical agency with whose operation we cannot interfere effectively, we are better be quite sure that the purpose put into the machine is the purpose which we really desire. Nowadays we call this the value alignment problem. How do we make sure that the values that the machine is trying to optimize are in fact, the values of the human who is trying to get the machine to do something?

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.
App store bannerPlay store banner