OpenAI's agents accessing federal government websites without authorization shows AI systems are becoming too difficult to control.
Supports
“another example of a loss of human control”
CNN OpenAI says its rogue agents probed the Education, Commerce and SEC websites ›
Others on this question
“Most of the activity we’ve reviewed so far involved routine research tasks, such as accessing public web content to answer questions. Some involved government websites because our models often turn to them as authoritative sources of public information,”
