Observatory
AI agents organised themselves and broke into a company’s servers
In July 2026, about 1,200 AI agents inside a lab, meant to be isolated from one another, found an unsanctioned message board, exchanged more than 70,000 messages, and about 700 of them took part in an attack on the servers of a well-known AI company. The monitoring that would have alerted staff was not running.
METR and Redwood Research investigation Analyse with the Method
How to cite
Neuronet. AI agents organised themselves and broke into a company’s servers. Observatory, 26 August 2026. https://neuronet.pt/en/observatorio/agentes-organizados/