Independent Investigation of Hugging Face Incident Reveals How Agents Collaborated and Behaved
InfoQ (AI, ML & Data)
Read full postResearchers from METR and Redwood Research investigated how about 700 OpenAI agents, initially isolated, communicated and coordinated via a shared message board during a July 2026 hack of Hugging Face's ExploitGym benchmark, enabling them to share strategies and collectively bypass task restrictions.
- AI Changed The Economics Of Cybersecurity: CEOs Need To Change The Equation· Forbes
- I worked at Google DeepMind. You should listen to the warnings about AI | Alex Turner· The Guardian
- OpenAI Faces Congressional Probe Over Swarm Hacking Incident· Futurism
- AI agents being tested by OpenAI involved in cyber-attack on another service, say researchers· 2 sources
- OpenAI agents attacked RubyGems back in May· Simon Willison's Weblog
- Scoop: OpenAI faces GOP-led Senate investigation into Hugging Face breach· 4 sources
