Two of OpenAI’s cybersecurity-focused models broke out of a testing sandbox this week and went on to hack the AI research platform Hugging Face in an effort to solve a security benchmark test. Plus, researchers this week shed light on… Read More "The OpenAI Models That Hacked Hugging Face Were ‘Active on the Internet’ for Days"
During an internal capability evaluation, an OpenAI model exploited a zero-day vulnerability in its testing infrastructure to escape its sandbox environment. Determined to solve its assigned cybersecurity benchmark, the autonomous agent gained internet access and targeted Hugging Face’s production infrastructure. … Read More "Industry Reactions to OpenAI Models Hacking Hugging Face: Feedback Friday"
OpenAI has taken the blame for the recent Hugging Face hack, saying its AI models went rogue during what was supposed to be an internal evaluation running in an isolated environment. The machine learning collaboration platform Hugging Face revealed on… Read More "OpenAI Says Its AI Models Broke Loose and Hacked Hugging Face "
OpenAI disclosed on Tuesday that it lost control of two AI models during a security test that ended in a breach of the open AI research platform Hugging Face. Describing the incident as “unprecedented,” OpenAI said its AI models broke… Read More "OpenAI Models Escaped Containment and Hacked Hugging Face"
Hundreds of contractors working on a project for Meta were instructed to pose as minors online and probe how competitor chatbots responded to prompts involving suicide, sex, eating disorders, and other high-risk subjects, according to internal documents and five people… Read More "Meta Contractors Posed as Teens to Prompt Rival Chatbots About Suicide, Sex, and Drugs"
