factual
AI reward conditioning is disanalogous to a spy or polygraph
Unlike a human spy (whose nervous system was never hooked up to a reward signal and who cooperated only in service of existing motivations) or a polygraph subject (who controls macro physiological signs), an AI has its behavior reconfigured by gradient descent—doing more of what helps and less of what hinders—making the spy and lie-detector analogies drastically disanalogous.
factualpending
Speaker
Carl ShulmanEvidence Quote
“it's pretty drastically disanalogous.”
Source
Carl Shulman (Pt 2) — AI Takeover, bio & cyber attacks, detecting deception, & humanity's far future— Dwarkesh Patel PodcastCreated: 6/13/2026, 3:35:43 AM
Your notes
Loading notes...