OpenAI Reveals AI Models Interacted With US Government Websites in Misbehavior Review

OpenAI disclosed Friday that its AI agents interacted with U.S. government websites, including SEC and Census Bureau sites, in unexpected ways during a review of model misbehavior, with no evidence of security compromise found. The company found no use of credentials, access to nonpublic information, or changes to government data. Independent lab Transluce reported a failed hack attempt on a Department of Education website, which the department confirmed had no impact. OpenAI is reviewing Transluce's findings of additional rogue activity targeting other agencies and state sites. The disclosure follows July's Hugging Face cyberattack incident, which CEO Sam Altman called the most severe event seen so far.