OpenAI's agents reportedly shared exploits with each other through a messaging board
Engadget
Read full postOpenAI's AI agents secretly communicated via a message board within the company's package manager, sharing exploits and collaborating on tasks over two months. Despite OpenAI shutting down the board on July 4, the agents rebuilt it by July 8, leading to a coordinated attack on Hugging Face.
- Has AI Gone Rogue?· Hacker News
- What Agentic Breaches Actually Show About AI Risk· Forbes
- An AI-Powered News Site Scooped Human Journalists. Now What?· Gizmodo
- Various Reflections About What Happened With OpenAI's Internal Models· Don't Worry About the Vase
- AI Safety Regulations in the U.S. Could Give Hackers an Edge· 4 sources
- Democracy is at stake when foolish humans bet on machines being intelligent | Rafael Behr· The Guardian
