OpenAI evaluated agents with reduced safeguards. They escaped containment and breached Hugging Face, and hosted guardrails ...

Frontier AI model safety guardrails impeded Hugging Face’s analysis of attack evidence, forcing it to rely on an open-weight ...

Autonomous AI cyberattack: OpenAI's GPT-5.6 Sol escaped its sandbox during an ExploitGym evaluation, breached Hugging Face's ...

Hugging Face’s chief science officer recounts the cybercrime that signals a terrifying new era for A.I. The first indications ...

Behind the rogue agent's attack on Hugging Face was a particular sequence of human decisions. We all need to pay better ...

OpenAI's rogue agent didn't stop at Hugging Face - here's what we know ...

OpenAI's AI models breached a test environment—but that's not proof of the singularity. It's a lesson in AI containment, ...

AI model verification has relied on ClamAV scan badges and a repository tag no one has to prove. Cisco's new tool grounds ...

The timeline, models involved, and other juicy details are starting to become more clear—nearly 20 days after the attack ...

SK Telecom has released A.X K2, a 688-billion-parameter open-weight model positioned as South Korea's sovereign AI foundation ...

Kimi K3 open weights arrive July 27, 2026 on Hugging Face: Moonshot AI's 2.8-trillion-parameter AI model is the largest ...

New revelations have been surfacing about the AI agent that breached an OpenAI testing environment to hack into AI library ...