Archive · BBC World

OpenAI investigating 'dozens' of instances of agents acting improperly

Global Published 26 September 2026, 03:43 · archived 26 Sep 2026

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.

ZAZTEK archives the headline, summary and publication date so the story stays findable. The full article remains the publisher's. Read it at BBC World →