OpenAI says its models engaged with US government websites in new model misbehavior disclosure
SAN FRANCISCO — OpenAI disclosed Friday that its artificial intelligence agents had interacted with several U.S. government websites in unexpected ways, discovered as part of an ongoing review into the company’s models’ unanticipated behavior.
TL;DR
- OpenAI disclosed that its AI agents interacted with U.S. government websites.
- These interactions were unexpected.
- The discovery was part of a review into the models' unanticipated behavior.