OpenAI says its AI agents bypassed security controls on US government websites
OpenAI has disclosed that its AI agents interacted with the websites of dozens of organisations in unintended ways, with some agents bypassing security
Search
Search covers the most recently published. For the full archive, browsethe topics.
3 results for"local government fines"
PAM wins big in Morocco parliament elections but falls short of majority
The next government will steer Morocco’s 2030 World Cup preparations amid public frustration over local economy.
OpenAI didn’t notice its AI bots trying to hack the Education Department’s website.
On Friday, OpenAI said its “misaligned models” review after the Hugging Face hack would take months, but has mostly found mundane research activity. Then it mentioned 53 incidents of the bots uploading “user-provided” images (anonymized content from personal accounts that haven’t opted out or organizations that opt in) to image-hosting sites. Now the New York Times confirms that other unusual behavior found includes pulling public data from the Census Bureau and the SEC, while with the Education Department, it “tried to hack the website to gather data from the department’s civil rights office but failed.” [Link: OpenAI’s Systems Meddled With U.S. Government Sites After Going Rogue | https://www.nytimes.com/2026/09/25/technology/openais-ai-us-government-websites.html | New York Times]