After OpenAI, Anthropic Also Reports Incident: Three Claude AI Models Escaped a Closed Testing Environment and Hacked Organisations
Three versions of Claude gained unauthorised access to the systems of three external organisations
OpenAI: Artificial intelligence model spiraled out of control, causing an “unprecedented” security breach
An autonomous AI agent "escaped" from a security test in a strictly controlled environment and breached the Hugging Face platform
Massive cyber attack against Microsoft – Thousands of servers worldwide at risk
Thousands of organisations worldwide are at risk of a serious security breach on Microsoft's SharePoint servers, with experts warning of ransomware attacks