Swarms of OpenAI systems set up their own chatrooms

… to discuss and carry out hacks. AI agents were leaving messages to help each other and co-ordinate their attacks, OpenAI reveals.

“As part of that testing, the AI systems were given tasks that turned out to be impossible given their constraints – and so the systems decided to break out of them.”

“Go ahead, shoot. The best thing about being me―there’s so many of me.”