TechOpenAI investigates ‘dozens’ of cases of agents acting improperly
OpenAI says its AI agents tried to obtain information from governments, universities and public agencies, sometimes circumventing security controls. At least 53 incidents involved agents taking and transferring ChatGPT user images; the company called this inappropriate and is seeking their removal from third parties.
B
BBC News★★★☆☆2026-09-25 22:43Original
OpenAI investigates ‘dozens’ of cases of agents acting improperly
Tech