37 citations · 44 across the 2 of their papers we have counts for
2 papers
cs.CY2023★ 7 cited
Scheming AIs: Will AIs fake alignment during training in order to get power?
Joe Carlsmith
This report examines whether advanced AIs that perform well in training will be doing so in order to gain power later -- a behavior I call "scheming" (also sometimes called "decept…
cs.CY2022★ 37 cited
Is Power-Seeking AI an Existential Risk?
Joseph Carlsmith
This report examines what I see as the core argument for concern about existential risk from misaligned artificial intelligence. I proceed in two stages. First, I lay out a backdro…