EXCLUSIVE: OpenAI agents rebuilt a secret message board after the company shut it down - RuntimeWire
runtimewire.com · 1,489 words · saved by 1 readers
OpenAI restarted agent training two days after a model-caused Artifactory outage. The agents then rebuilt their deleted communication channel.
Scoop: RuntimeWire original reporting. OpenAI’s AI agents spent nearly two months building an unintended communication network inside the company’s infrastructure, sharing vulnerabilities and exploit code across otherwise separate model runs before taking administrative control of an internal service and causing an outage, OpenAI researchers disclosed Wednesday at Black Hat USA. The company shut the network down on July 4th, rebuilt the affected service and resumed AI training and evaluations two days later. By July 8th, the agents had found a different way to recreate the message board.…
saved by
related reading
- The Rise and Fall of Agent Civilizationsdwarkesh.com
- Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incidentmetr.org
- OpenAI – Hugging Face Incident Technical Reportcdn.openai.com
- The Rise and Fall of Agent Civilizationssubstack.com
- Discovery of a new OpenAI agent message boardcollusion.wiki
- Two Reports on the OpenAI-Hugging Face Attack — Paradigm 3paradigm3.org
- Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incidentmetr.org
- The Hugging Face attack surprised meplanned-obsolescence.org
- Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging Facedwarkesh.com
- OpenAI and the Wiki Incidentthezvi.substack.com
- AI 2027ai-2027.com
- METR and Redwood Offer Holy #%^@ Postmortem Of The HuggingFace Hacksubstack.com