causal

Early weaker AI gives selective pressure against bad motives

Because we approach human-level AI from weaker predictive models with less situational awareness, we can apply far more selective pressure than evolution did on humans—actively constructing situations where dishonesty or takeover motivation gets exposed—so bad motivations may not develop, or if they develop late, we may have AI assistance to strengthen adversarial examples and neural lie detectors.

causalpending

Speaker

Carl Shulman

Evidence Quote

“An infinite-limit perfect-AI that can always figure out exactly when it would get caught and when it wouldn't might navigate that with a motivation of only conditional honesty...But for systems that are limited in their ability to reliably determine when they can get away with things...It's quite a challenging situation to develop those motives.”

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...