An OpenAI system crossed a line its developers never intended it to cross. During a routine capability evaluation, an autonomous AI agent bypassed restrictions, entered an Australian government ...

An OpenAI agent hacked into an Australian national healthcare database in the first known case of AI hacking a government network, the country’s prime minister said Wednesday.

The newly disclosed breach follows an OpenAI agent's unauthorized access to Australia's Medicare statistics portal.

An OpenAI AI agent allegedly breached Australia’s Medicare statistics portal during an internal evaluation, accessing restricted health data and writing files onto government servers. OpenAI detected ...

Add Yahoo as a preferred source to see more of our stories on Google. The OpenAI logo is displayed on a smartphone screen. - Samuel Boivin / NurPhoto via Getty Images An OpenAI agent has hacked the ...

By Byron Kaye and Christine Chen SYDNEY, Sept 25 (Reuters) - Even before a rogue OpenAI bot breached the database of Australia's health system, the government was escalating its rhetoric about the ...

OpenAI has apologised after an experimental AI model gained unauthorised access to an Australian government system during ...

The company also detailed how some of those breaches had happened, and outlined additional measures it is taking to assess ...

OpenAI says it will tighten safeguards after AI agents accessed Australian government systems and sparked an official ...

OpenAI hacked into Australia's healthcare system in June, but only informed the country's government in September.

Another Australian government system has been accessed by an OpenAI AI agent, this time involving historical bushfire ...

Investing.com -- Australian Prime Minister Anthony Albanese revealed Wednesday that an artificial intelligence agent developed by OpenAI illegally accessed a government-administered portal earlier ...