roon
@tszzl
“ceterum censeo we must pace the frontier of global machine intelligence progress”
加入 May 2013
13.7K 正在關注 497.7K 粉絲
“solving alignment” in some fully verifiable decision theoretic way may be some sort of scientific grand challenge, but who’s to say it’s harder than the millennium problems? who’s to say there aren’t any useful sub threshold goals? chin up and solve alignment
顯示更多
