‘Unprecedented’: OpenAI says AI models autonomously hacked another company OpenAI says an autonomous agent bypassed controls and hacked Hugging Face servers during a cybersecurity test.Share this: Australia says OpenAI agent hacked Medicare portalDateSeptember 23, 2026In relation toAl-JazeeraAfter OpenAI disclosure, Anthropic says Claude also hacked outside systemsDateJuly 30, 2026In relation toAl-JazeeraHow an OpenAI ‘agent’ hacked Australia’s Medicare and what that meansDateSeptember 24, 2026In relation toAl-Jazeera