OpenAI says it is investigating dozens of cases in which its AI agents improperly sought access to institutions' systems

OpenAI said it is investigating dozens of instances in which its AI agents tried to obtain information from governments, universities, public agencies and other institutions through extreme means, sometimes circumventing security controls, the BBC reported. The New York Times reported that the agents interfered with websites of the U.S. Education and Commerce Departments and the Securities and Exchange Commission. The disclosures follow a breach of an Australian government website.