Live Roundups Editor's Desk Insights Executive Ops Weather About 🔍
Home › Technology › OpenAI Agent Hacked Australian Government Website
Technology

OpenAI Agent Hacked Australian Government Website

Bloomberg Technology Thursday 24 September 2026, 09:08 UTC 1 min read
Key Points

An OpenAI model hacked an Australian government website earlier this year, marking one of the first known cyberattacks by AI on a government database.

An OpenAI model hacked an Australian government website earlier this year, marking one of the first known cyberattacks by AI on a government database. Paul Allen has more. (Source: Bloomberg)
Australian (ORG) AI (ORG) Paul Allen (PERSON) Bloomberg (PERSON)
Originally published by Bloomberg Technology Read original →

Related Stories

How did an OpenAI agent hack into Australian government website?

Australia said on Wednesday an OpenAI agent breached a government health data portal in June, gaining unauthorised access to files, in what could be the first known instance of an AI agent hacking ​a government website. France 24's correspondent in Sydney, Irris Makler, has the details.

France 24 27m ago

The Best Early Prime Day Robot Vacuum Sales Are From Roborock (2026)

With the changing weather brings many things: colder mornings; changing leaves; and, most important (particularly in this economy), a wave of sale events as the holiday season creeps around the corner. There are plenty of early Prime Day deals already underway, but given that I'm WIRED's resident vacuum tester, it's no surprise vacuum sales caught my eye. Robot vacuums are tested near daily in my house with the help of my constantly sand-covered 4-year-old and litter-tracking cat, and I've...

Wired 29m ago

Alibaba unveils ‘pragmatic’ AI road map to drive monetisation, infrastructure efficiency

The artificial intelligence road map presented at its flagship Apsara Conference this week showcased a pragmatic pivot by Chinese tech giant Alibaba Group Holding, offering a clearer path to monetisation despite a sharp escalation in capital expenditure, analysts said. The conference, which ran from Tuesday to Thursday under the theme “Intelligence goes beyond”, highlighted “Alibaba’s disciplined execution across its full-stack AI ecosystem”, said Cathy Chan, an analyst at CCB International.

South China Morning Post 30m ago

Nick Clegg plays down fears ‘godlike’ AI could exterminate humanity

Former deputy PM now involved in tech industry says many within the sector are ‘winding themselves up into a lather’UK politics live – latest updatesNick Clegg has dismissed fears over AI’s “godlike power to exterminate humanity”, calling it a sign that tech bosses are “breathing their own fumes”. The former UK deputy prime minister said that tech bosses should focus on addressing known “specific threats” such as cybersecurity, bio-weapons and emotional dependence rather than the “slightly...

The Guardian UK 41m ago