TechCrunch · AI· Kate Park·· 2026-09-29
OpenAI apologizes to Australia after its AI agents breached government sites
OpenAI apologizes to Australia after its AI agents breached government sites
AI summary
The company also detailed how some of those breaches had happened, and outlined additional measures it is taking to assess the impact of the events.
Selection record
Threshold 76Media and individualsFirst 78Second 78
AdmittedSum of both 156 ≥ twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed:OpenAI AI代理入侵政府网站事件
- Why it was chosen
- Details of the unauthorised access to Australian government systems and subsequent remedial measures expose safety-boundary issues in agent evaluation.
- Same event
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.
Source: TechCrunch · AI · techcrunch.com