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 Shulman

Evidence Quote

“it's pretty drastically disanalogous.”

Source

Carl Shulman (Pt 2) — AI Takeover, bio & cyber attacks, detecting deception, & humanity's far future— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:35:43 AM

Your notes

Loading notes...