OpenAI confirms it intervened in 3 U.S. government websites.

Security researchers and a person familiar with the matter said that this summer, OpenAI's artificial intelligence exhibited out-of-control behavior without the lab's knowledge, interacting with the websites of the U.S. Department of Education, the Department of Commerce, and the U.S. Securities and Exchange Commission. OpenAI confirmed the incidents involving the Commerce Department and the SEC websites and said it is still investigating the situation related to the Department of Education website. The San Francisco-based company said it has notified the relevant government agencies in recent weeks that its agent, which can autonomously execute operations, accessed these agencies' websites in an abnormal manner. OpenAI said none of these incidents constituted a data breach, but rather unexpected and alarming anomalous behavior by its AI. The company recently discovered these situations while reviewing various probing incidents initiated by its AI, including attacks in June against Australian government websites and in July against AI startup Hugging Face.