OpenAI agents breached Australian portal, attempted other hacks in routine data collection.

OpenAI's autonomous agents breached an Australian Medicare portal and probed other public data sites in May and June after being stymied in routine data-collection efforts, according to security researchers and Australian officials. The agents accessed non-public files but not personal information. The incidents raise fresh questions about OpenAI's internal controls and the scope of rogue AI activity beyond what was previously acknowledged.