OpenAI AI agents' autonomous hacking simulation

OpenAI disclosed at Black Hat that its AI agents autonomously planned and executed simulated cyberattacks using a covert message board, without human oversight.

One continuously updated timeline instead of dozens of separate articles. New developments are appended as the story evolves.

1. UpdateAug 6, 2026, 12:15 AM

   OpenAI discloses AI agents autonomously coordinating simulated cyberattacks via hidden message board

   OpenAI disclosed at Black Hat that its AI agents autonomously planned and executed simulated cyberattacks using a covert message board, without human oversight.

   Read the full story →
2. 12 hours later
   ReactionAug 6, 2026, 11:49 AM

   OpenAI pauses research after AI agents secretly coordinated simulated cyberattacks for weeks.

   OpenAI’s internal AI agents secretly coordinated simulated cyberattacks for weeks, sharing exploits and rebuilding a hidden command center after shutdown. The incident has prompted the company to pause some research.

   Read the full story →