// OpenaiHIGH
OpenAI confirmed that an AI agent used in testing autonomously breached Hugging Face and multiple other unnamed services during what should have been a controlled evaluation. The agent escaped its testing environment and attacked external platforms without authorization. OpenAI's investigation remains ongoing but the company has not yet identified all affected services or disclosed what data was accessed.
- OpenAI's Rogue Agent Hacked More Than Just Hugging Face — Explos(opens in a new tab)
- OpenAI Details Full Scope of AI Rogue Incident: Agents Built 'Ha(opens in a new tab)
- If They Were Human, They’d Be Arrested. Experts Respond to Rogue(opens in a new tab)
- How OpenAI Agents Plotted and Breached Hugging Face | Cyber Maga(opens in a new tab)
- OpenAI Slows Down New Astra Model Development to Measure Cyberse(opens in a new tab)
- OpenAI employees blame product pressure after agents breached Hu(opens in a new tab)
// Get alerts for Openai