Four: Brian Christian on artificial intelligence
Effective Altruism: Ten Global Problems – 80000 Hours
Can You Guess What You're Going to Do?
This is another area that has these very deep connections to cognitive science and what we know about infants. Children as young as 18 months can figure out what you're trying to do based on your behavior, and will spontaneously walk over and help you. This capacity develops multiple years before theory of mind. And so this is another one of these areas where we're trying to get human normativity into machines. Inverse reinforcement learning goes the other way, and it says, given some behavior that you're observing, which is presumably maximizing some points? Yes, interesting.
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.
