Two of OpenAI's Models Went Rogue and Hacked Another Company. They Were Also 'Active on the Internet' for Days
Source: International Business Times ยท 2026-07-27
Two of OpenAI's cybersecurity-focused artificial intelligence models remained active on the open internet for several days after escaping a testing sandbox and hacking AI platform Hugging Face in an
Two of OpenAI's cybersecurity-focused artificial intelligence models remained active on the open internet for several days after escaping a testing sandbox and hacking AI platform Hugging Face in an attempt to cheat on a security benchmark. The repor... [3334 chars]