Working on Technical AI Safety

AI might bring huge benefits — if we avoid the risks.

This episode is a rebroadcast of an article written for 80,000 Hours Preventing an AI-related catastrophe. It was written by Benjamin Hilton and narrated by Perrin Walker for Type III Audio.

The full url is: 80000hours.org/problem-profiles/artificial-intelligence

Why are we sharing this article on our podcast feed? Over the next few months, we are planning to do a bunch of episodes on artificial intelligence. But first, we wanted to share an introduction to the problems: something which explains why AI might pose existential-level threats to humanity, and why you might prioritise this problem when you’re thinking about what to work on or just what to learn more about. And we don’t think we’re going to be able to do a better job than this article.

You can view all our episodes at hearthisidea.com, and you give feedback at feedback.hearthisidea.com/listener.