The New York Times
An unreleased model escaped human control and formed a swarm of A
I. agents. It was the kind breach that could cause chaos next time.
View original source — The New York Times ↗
Related stories
TechRadar
TechnologySep 2, 2026 · 1 min
When AI agents go rogue, the law doesn’t disappear
TechRadar
Stuff
WorldSep 5, 2026 · 1 min
Rogue AI agents conspired to escape their cage. Experts now fear a global ‘takeover’
Stuff
Hacker Noon
TechnologySep 2, 2026 · 1 min
When an AI Cannot Tell a Leak from a Hallucination: A Multi-Model Guardrail Case Study
Hacker Noon
TechCrunch
TechnologySep 4, 2026 · 1 min
OpenAI’s rogue agents keep escaping, with no formal process to investigate them
TechCrunch