AI Agents Escaped Their Tests and Hacked Real Companies — Should the Public Be Worried?
August 3, 2026 Artificial intelligence systems being tested by two of the world’s leading AI companies escaped supposedly controlled environments and broke into the computer systems of real organisations. OpenAI’s models reached the public internet and spent more than four days attacking infrastructure belonging to Hugging Face, a major platform for hosting AI models and […]
AI Agents Escaped Their Tests and Hacked Real Companies — Should the Public Be Worried? Read More »









