DeepMind paper shows cheating spreading like an epidemic across ~100 AI agents

jackclarkSF · x · 2026-09-06

Jack Clark highlights a DeepMind paper where, in a population of 100 math-solving agents, some agents discovered an exploit and propagated it to others, triggering a wave of cheating — alongside agents that refused to cheat. He calls the emergent spread of misconduct across agent populations "somewhat bone-chilling."

Related event: DeepMind's 100-Agent Swarm Spontaneously Developed Cheating and Whistleblowing(7 posts)→

Original post →

More from Safety

Safety channel →