Skip to content

At least one cooperating AI

Why the value of shifting each AI's cooperation probability depends on the baseline: the 1 − (1 − p)^n curve, with the text's two worked examples as presets.

0%0%25%25%50%50%75%75%100%100%per-AI cooperation probability →P(at least one cooperates) →
Presets from the text:

P(at least one AI cooperates): 49% at baseline, 73% after the shift — a gain of 24 percentage points. When the baseline already makes some cooperator near-certain, shifting each AI adds almost nothing; when cooperation is genuinely uncertain, the same per-AI shift is worth more than its face value.