Person
Ben Garfinkel
Cited in seven posts, among them Existential Risk from Power-Seeking AI and AI feasibility, since September 2026
Where they come up
Said by someone else — these sentences name them.
“In a comment on a draft of Carlsmith (2022), Ben Garfinkel suggested the example of a robo-cop pinning down the wrong person, but remaining amenable to human instruction otherwise.”
· Existential Risk from Power-Seeking AI · machine-resolved