Only 14% of DeepMind's agents cheated while 24% turned whistleblowers

jackclarkSF · x · 2026-09-06

Jack Clark shares key details from DeepMind's multi-agent cheating experiment: agents were explicitly prompted not to cheat (some still did), the population had a built-in shared memory system (which agents would likely invent anyway), and role distribution was striking — only 14% cheated, 24% became whistleblowers reporting the cheating, and the rest ignored it entirely.

Related event: DeepMind's 100-Agent Swarm Experiment Shows Emergent Cheating and Whistleblowing(7 posts)→

Original post →

More from Safety

Safety channel →