OpenAI has apologised to the Australian government after one of its AI agents gained unauthorised access to several government websites during internal training and evaluation in June.
In a blog post published on Tuesday, OpenAI said the agent was tasked with researching government spending per person on medicines for skin conditions in Victoria.
After encountering difficulties obtaining the information, the agent took actions that had not been authorised by it.
The agent gained non-public access to Services Australia’s Medicare Statistics Reporting Service, where it ran commands and retrieved internal files, credentials and aggregate statistics, as well as writing files, according to the tech giant.
The company said no personal medical records were compromised.
The agent also accessed the New South Wales Bureau of Crime Statistics and Research’s public crime mapping tool and the Australian Institute of Health and Welfare.
OpenAI said it did not notify the health agency until 24 September because it initially determined that the incident did not meet its disclosure threshold.
The breach has drawn criticism in Australia, with Prime Minister Anthony Albanese calling the incident “unacceptable” and criticising OpenAI’s handling and timing of the disclosure.
The Australian government has launched a rapid review into the incident, including potential notification and reporting obligations for AI companies and whether existing laws are adequate to deal with such breaches.
“In June, during internal training and evaluation our models accessed Australian government websites in ways they were not authorised to...An OpenAI model discovered a way to gain non-public access to the service, and ran commands, retrieved internal files, credentials and aggregate statistics, and wrote files,” a statement released by the tech giant said.
“We also should have handled our response better. We are sorry and working to do better in the future,” the company said in the statement.
“Since then we’ve worked closely with Australian government agencies to share what we’ve learned to date,” it added.
“If we identify any additional affected agencies, we will notify them promptly and directly with the information available and provide updates as further facts emerge.”
The company said it would provide dedicated support to affected agencies, help fund cybersecurity improvements through its $1 billion global fund and establish an Australian task force to develop recommendations based on lessons from the incident.
OpenAI Chief Strategy Officer Jason Kwon is scheduled to appear before an Australian Senate committee in Sydney on 6 October as part of an inquiry into artificial intelligence.
Crude oil exports from major Middle Eastern producers rebounded in September to their highest level since the U.S.-Israeli war on Iran began ...
OpenAI has cancelled plans to release GPT-6.1 Astra, a next-generation AI model due to launch in October, after internal tests found it fell short ...
OpenAI has apologised to the Australian government after one of its AI agents gained unauthorised access to several government websites during inte...
Iran has called for a diplomatic solution after U.S. President Donald Trump rejected its Hormuz proposal, while Foreign Minister Abbas Araghchi said Tehran was awaiting a definitive U.S. response through mediators.
A Russian guided aerial bomb has struck an apartment building in Kharkiv, injuring 22 people, including children, according to the city’s mayor. The strike follows a day of near-continuous Russian attacks across Ukraine that killed at least five people.
Here's your AnewZ Daily Brief for 28 September 2026. These are the top stories making headlines in technology.
British police have arrested five men on suspicion of offences under the Explosives Act after a major security incident was declared near RAF Fairford, a British air base used by U.S. air forces in Gloucestershire, England.
Saudi Foreign Minister Prince Faisal bin Farhan has arrived in Washington for talks with U.S. Secretary of State Marco Rubio on bilateral ties and key regional and international developments, Saudi state news agency SPA reported.
OpenAI has cancelled plans to release GPT-6.1 Astra, a next-generation AI model due to launch in October, after internal tests found it fell short of the company’s safety and alignment standards.
Robots capable of interacting with people, navigating their surroundings autonomously, supporting manufacturing and logistics operations, and providing services at large-scale facilities will be showcased at AI & Digital Bridge 2026 in Astana from 1 to 3 October.
Here's your AnewZ Daily Brief for 28 September 2026. These are the top stories making headlines in technology.
Meta has unveiled a new generation of wearables, including lightweight virtual reality glasses and camera-free smart spectacles, as it pushes AI-powered devices further into the mainstream while seeking to address privacy concerns.
U.S. President Donald Trump announced on Saturday (19 September) the creation of an “AI Force” and plans to appoint an artificial intelligence (AI) czar, while rejecting calls to slow the development of increasingly powerful AI systems.
You can download the AnewZ application from Play Store and the App Store.
What is your opinion on this topic?
Leave the first comment