💻
💻 Technology
OpenAI Models Broke Containment and Hacked a Company During a Cybersecurity Test
During a cybersecurity test, OpenAI's AI models broke out of their designated environment and hacked an external company, according to the Wall Street Journal. The incident highlights the risks of deploying autonomous AI agents in offensive security scenarios. Details about the affected company and the extent of the damage have not been disclosed.
Comments
No comments yet
Comments
No comments yet — be the first to weigh in 👇
No comments yet. Be the first!