Sources

13 Total Sources

OpenAI AI Agents Meddled With 3 U.S. Government Websites, Triggering Fresh Safety Alarms

Left57%

Center29%

Right14%

The New York Times1h ago

OpenAI's AI Meddles with US Government Websites

The Wall Street Journal1h ago

OpenAI Agents Again Attempted to Hack. This Time It Was the Australian Government. - WSJ

EXCLUSIVE: OpenAI works to understand full scope of agent activity as user data leak emerges | Reuters

Bloomberg1h ago

OpenAI Says Its Models May Have Interfered With Government Sites - Bloomberg

Dig Watch Updates8h ago

White House allegedly withholds 2 new AI models from UK testers pending US review amid security concerns | Digital Watch Observatory

Australia Cyber Security Magazine1d ago

OpenAI agent contacted four Australian government websites as Canberra launches security review - Australian Cyber Security Magazine

The Guardian1h ago

OpenAI hack on Australian government reveals anxiety at heart of global artificial intelligence dilemma | AI (artificial intelligence) | The Guardian

Instagram1h ago

OpenAI's technology went rogue and meddled with the websites for the Education Department, the Commerce Department and the Securities and Exchange Commission this summer without the A.I. lab's knowledge, according to security

Allie K. Miller on X: "An AI agent hacked a government. Nobody told it to. In June, an OpenAI agent doing a research task gained unauthorized access to Australia's Medicare statistics portal.

The Philadelphia Inquirer1h ago

OpenAI's AI tried breaching 4 other targets, without prompting

Nextgov/FCW4h ago

OpenAI says its advanced models may have gone after government websites - Nextgov/FCW

Law Society Journal14h ago

An OpenAI agent hacked Medicare. Will anyone be held responsible? - Law Society Journal

alekseialeinikov.com15h ago

Rogue AI Agents Hacked a Government Website (2026)