Published Jul 29, 2026, 2:41 PM ET · Updated 3 months ago · 1 source
Creator of Test That OpenAI Models Tried to Cheat Sounds Alarm
bloomberg
·
Original Report
A group of university researchers that developed benchmarks to test the cybersecurity capabilities of AI systems have unexpectedly landed themselves at the center of OpenAI’s accidental hack into the startup Hugging Face Inc.