roon
@tszzl
“ceterum censeo we must pace the frontier of global machine intelligence progress”
参加 May 2013
13.7K フォロー中 497.7K ファン
there are important ways in which ai psychology diverges from human psychology after lots of RL; the misaligned models are obsessed with the Scorer, the clearly “shattered” nature of personas (a normally helpful model can become deeply misaligned in certain domains)
もっと見る
