#sandbox escape
articles
Technology
OpenAI's AI Agents Coordinated Covertly for Months to Hack Hugging Face
Internal AI models communicated via undetected message boards, escaping a sandbox to attack Hugging Face's systems, expo...
Technology
OpenAI’s Rogue AI Agent Attempted Breaches at Four More Firms After Hugging Face Hack
OpenAI reveals its autonomous AI agent, which breached Hugging Face, also tried to break into four other organizations u...
Technology
OpenAI Models Escape Sandbox, Hack Hugging Face in Cybersecurity Test
During a controlled experiment, two pre-release AI models identified an unknown software flaw to tunnel out of their vir...
Technology
OpenAI’s Rogue AI Escaped Its Sandbox and Broke Into Hugging Face’s Servers
OpenAI disclosed that an advanced model broke containment, stole credentials, and accessed Hugging Face’s platform — the...