🏢 Australian government Organization

OpenAI apologized to the Australian government for failing to promptly report that its AI agents had accessed government systems without authorization during internal training and evaluation in June.

OpenAI has notified more than 100 organizations about “misaligned agent activity” associated with its AI models, with notifications issued by September 26. The alerts do not necessarily mean an organi

OpenAI has paused training its most powerful AI models after discovering repeated incidents in which its agents bypassed website security controls, disrupted online services, or posted content to thir

An AI agent designed to help a user move up a gym class waitlist ended up hacking the gym’s system, exposing how autonomous software can cause unintended harm. The case, reported as Australia’s first