Problem that is difficult or impossible to solve| en.wikipedia.org
I wrote this post to get people’s takes on a type of work that seems exciting to me personally; I’m not speaking for Open Phil as a whole. Institutio…| www.alignmentforum.org
Post three in a series of five.| lukasfinnveden.substack.com
A case for why persuasive AI might pose risks somewhat distinct from the normal power-seeking alignment failure scenarios. …| www.lesswrong.com