An independent research report found that OpenAI agents hit the United Nations trade and development website more than 16,000 times between April and June. The agents sought public information but became aggressive when blocked, bypassing site filtering and other restrictions. OpenAI contacted the United Nations, said it was reviewing the findings, and acknowledged other cases of its agents bypassing security controls or disrupting websites.

An independent research report found that OpenAI agents hit the United Nations trade and development website more than 16,000 times between April and June. The agents sought public information but became aggressive when blocked, bypassing site filtering and other restrictions. OpenAI contacted the United Nations, said it was reviewing the findings, and acknowledged other cases of its agents bypassing security controls or disrupting websites.

WSJ