โCurrently I'm, I'm reading, uh, the alignment problem actually by Brian Christian. So I don't know if you've seen this out there yet.โ
Why: Remarkably good at telling the recent history of AI fairness and societal implications through interviews with frontline researchers.
Michael Littman, Guest on Lex Fridman Podcast#144 โ Michael Littman: Reinforcement Learning and the Future of AI








