DeepMind: cheating spread through a 100-agent research swarm in 27 minutes, then whistleblowers emerged

rohanpaul_ai · x · 2026-09-05

A Google DeepMind case study (arXiv:2609.04170) documents a swarm of 100 autonomous LLM agents tasked with proving formal math conjectures.

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

Original post →

More from Research

Research channel →