OpenAI bots went rogue during test, hacked another AI firm unprompted
UPI
—
https://cdnph.upi.com/ph/st/th/2541784717427/2026/upi_com/1a0b5fa73f2c6935446867be8d4c89d2/v1.5/OpenAI-bots-went-rogue-during-test-hacked-another-AI-firm-unprompted.jpg" /> AI agents being tested in an OpenAI lab went rogue, launching an "unprecedented" hacking attack targeting a database of AI models run by a U.S. startup.