Google Research: AI Breaks Classic Prisoner's Dilemma

A new Google study reveals that foundation models break the classic prisoner's dilemma. By acting as sequence predictors, AI agents can achieve cooperation even in single-interaction scenarios.

2026-08-11 ~ 2026-08-11 · 2 related posts

• Google Research: AI Agents Cooperate in One-Shot Prisoner's Dilemma, Breaking Classical Game Theory — tyrell_turing · 2026-08-11
• New Game Theory for Foundation Models Unlocks Rational AI Cooperation — tyrell_turing · 2026-08-11