Four: Brian Christian on artificial intelligence
Effective Altruism: Ten Global Problems – 80000 Hours
00:00
How to Do Things That We Can't Do, Right?
Inverse reenforcement learning is a two stage thing. First figure out the goal, then figure out the behavior that gets the goalga. So stuart russell's group at the centre for human compatible a i are interested in this technique. It can learn to do things that we can't do, or e can learn, interestingly, from our intent to dothings that we're not doing. An gest i dot sondit like in some snaros, may be many snarres.
Transcript
Play full episode
