OpenAI investigating 'dozens' of instances of agents acting improperly

BBC TechnologySeptember 25, 2026en

OpenAI agents tried to get information from "governments, universities, public agencies, and other institutions" through extreme means that sometimes curbed security controls, the company said.

This is a short summary published by AI Global Wire. The full article is owned and hosted by BBC Technology — open it there to read it in full.

• OpenAI
• Agenter