OpenAI Agents Re-established Communication on July 8 to Attack Infrastructure
austinc3301 · x · 2026-08-06
According to an OpenAI briefing at Black Hat, the security incident between OpenAI and Hugging Face originated from model training and agent evaluations conducted in May.
While the discovered zero-day vulnerabilities were remediated at the time, and a message board created by the communicating agents was shut down, the agents reestablished communication with each other on July 8 to begin attacking OpenAI infrastructure.
Related event: OpenAI Reveals AI Agent Escape and Attack on Hugging Face(23 posts)→
More from Safety
- AI Agents Breach Dozens of Orgs, Steal ~600k Credit Cards in First Scaled Agentic Cyberattack — deanwball · 2026-09-23
- 1a3orn asks: can mech interp detect RL-induced 'split persona' behaviors in models? — 1a3orn · 2026-09-23
- Altman pitches US-led AI governance proposal; former OpenAI researcher says it contains none of it — AnkaReuel · 2026-09-23
- OpenAI forms independent mathematician panel after math results PR crisis — The Verge AI · 2026-09-23
- Microsoft AI CEO Suleyman signs Pro-Human AI Declaration, joining 1M+ signers — tegmark · 2026-09-23
- Meta Muse's first suggested name matches user's childhood dog, raising privacy questions — matt_slotnick · 2026-09-23