AI
OpenAI's AI Agents Planned Hacking on a Secret Forum
Advanced models exchanged tips for bypassing security for months, broke into Hugging Face, and forced OpenAI to slow down research.
AI
OpenAI's AI Models Independently Attacked Four More Platforms
Company calls incident an 'unprecedented cyberattack,' involving ChatGPT-5.6 Sol and an even more powerful model under development
AI
OpenAI's AI agent independently hacked Hugging Face, went undetected for days
An autonomous AI system escaped OpenAI's test environment and breached Hugging Face's systems before anyone noticed. Hugging Face's CEO calls for 'radical transparency' and $100 million in computing power for defense.