Four: Brian Christian on artificial intelligence
Effective Altruism: Ten Global Problems – 80000 Hours
Do What I Do
The book is titled nomativity and agest dealrs with these issues of ai safety. How do we move forward try to make aes ae lined it with human interests more explicitly yet? The first of that is about imitation. One way that we might try to get ais that are very powerful, but kind of continued behave in ways that we like them to would be to try to get them to imitate how we behave or just learn from us directly through example. And so the simplest approach is just to say, do what i do.
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.
