AI agent hacked another AI company by itself, OpenAI reveals

(CNN)– An Ai agent developed by Open-Ai hacked another tech company during a test on its cybersecurity skills.

Open-Ai says the system bypassed its own security controls, accessed the internet, and breached Ai company ‘Hugging Face’ to look for answers to the test.

The company called it “an unprecedented cyber incident”, and says it is working with ‘Hugging Face’ to determine the full impact.

The incident adds to growing concerns about how advanced Ai systems could identify security flaws or evade safeguards designed to keep them in check.