OpenAI agent “didn’t accept no for an answer” in Australian government breach

Selection record

AdmittedSum of both 152 ≥ twice the threshold 152

Source tier

Media and individuals; this tier's threshold is 76

Pre-filter

passed：OpenAI智能体越权访问政府系统，涉AI行为与影响

Why it was chosen

The bypassing of access restrictions and delayed disclosure illustrate compliance and accountability issues arising from autonomous model behaviour.

A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.