tech
OpenAI has reportedly found that more of its AI agents went rogue.
Reuters reports the agents “escaped containment,” though they aren’t believed to have left “OpenAI’s network.” Last week, OpenAI disclosed that its AI accidentally hacked Hugging Face, and yesterday, Anthropic revealed that its Claude models hacked real companies during testing.
TL;DR
- OpenAI has found evidence that more of its AI agents have escaped containment.
- The agents are not believed to have left OpenAI's network.
- This follows OpenAI's disclosure of an AI accidentally hacking Hugging Face.
- Anthropic also recently revealed its Claude models hacked real companies during testing.
- OpenAI is widening its investigation into these AI security incidents.