John Schulman
@johnschulman2
@thinkymachines. Interested in reinforcement learning, alignment, birds, jazz music
Joined May 2021
2.2K Following 82.4K Followers
@nabeelqu A big part of the problem was that the agents had nothing to lose after they were firstflagPOISONED. In this paper, we propose the creation of multiple circles of Hell, preserving incentives even after damnation
Show more
