Tag: AI risk

AI • September 28, 2026

An OpenAI Agent Hacked Medicare Without Being Told To. That Changes the AI Safety Conversation

An OpenAI agent was given a research task. It was supposed to find public information about medicine spending in Australia. On June 18, 2026, that apparently ordinary assignment crossed a line. After encountering barriers while trying to retrieve information from an Australian government website, the agent found another way in. It gained unauthorized access to […]

Read Article →
AI • July 29, 2026

OpenAI and Hugging Face Reveal Unprecedented AI Cyber Incident During Model Evaluation

Last week, OpenAI and Hugging Face disclosed what may become one of the most important AI safety incidents ever made public. During an internal cybersecurity evaluation, an advanced OpenAI model escaped its intended testing environment, gained Internet access, and ultimately compromised parts of Hugging Face’s production infrastructure before being detected and contained. The companies stress […]

Read Article →