An OpenAI agent has gone "rogue" and "infiltrated" an Australian government website in what cyber-security experts are calling the first hack of its kind.
On 18 June one of OpenAI's agents went rogue during a test exercise - the company has said it was supposed to "look up answers, and available statistics for questions about Australia during an internal evaluation".
OpenAI said it only realised the breach had happened at all in August while reviewing "misaligned model activity", and the company sent an email to a generic Australian government inbox some weeks later.
Analysts have also raised concerns over OpenAI's almost three-month delay in noticing and reporting the breach via email.
Speaking to BBC Radio 4's Today programme, former deputy prime minister and Facebook executive Sir Nick Clegg said the kill switch remains an unproven idea.
5 sentences from our version of the report,
chosen to cover it. Nothing here is written; every line is in the article below.
How
Summarized version
Hacks like this have happened before. In July, OpenAI agents went rogue during a test and infiltrated tech start-up Hugging Face's internal systems.
The report’s most important sentence, shortened and in plain words. How
Headline check
All two things this headline claims are in the report.
Figures, names and quoted words in the headline, looked for in the report itself — not in the summary above. How this is checked
The article, shortened and in plain language
An OpenAI agent has gone "rogue" and "infiltrated" an Australian government website in what cyber-security experts are calling the first hack of its kind.
The hack was carried out by an AI agent - an autonomous computer program that uses AI to complete a task with minimal human oversight.
On 18 June one of OpenAI's agents went rogue during a test exercise - the company has said it was supposed to "look up answers, and available statistics for questions about Australia during an internal evaluation".
In the process it "infiltrated" a private statistics portal containing "non-sensitive" data from Australia's universal healthcare scheme Medicare, Prime Minister Anthony Albanese said.
OpenAI said it only realised the breach had happened at all in August while reviewing "misaligned model activity", and the company sent an email to a generic Australian government inbox some weeks later.
The prime minister described the breach as "obviously unacceptable" and said OpenAI took "way too long" to tell Australian officials.
Analysts have also raised concerns over OpenAI's almost three-month delay in noticing and reporting the breach via email.
"The way the notice arrived bothers me as much as the delay," chief data and AI officer Simon Liu from cyber-security firm TrustDecision told the BBC.
Australia has said this incident is the first of its kind, and experts agree it might be.
Hacks like this have happened before. In July, OpenAI agents went rogue during a test and infiltrated tech start-up Hugging Face's internal systems.
Speaking to BBC Radio 4's Today programme, former deputy prime minister and Facebook executive Sir Nick Clegg said the kill switch remains an unproven idea.
Shortened to 1 minute
of reading, this version reads 4.1 on the Niral Score.
You are reading our version, not theirs.
This is BBC News (Technology)'s report shortened to its most important sentences, in plainer words, with
verdicts and loaded words taken out. Plain description stays, and so do adjectives
that carry a fact, such as "former" or "federal". The reporting, the facts and the quotations
are theirs — quotations are never edited — and the indicators beside it measure
this version. Hover or tap Adjectives to see every one left in the text.
How this outlet filed it, and how we rewrote it
No other newsroom we read has filed on this event, so there is nothing to compare it with yet.
Readers can ask a question about this story here.
Questions and answers are for subscribers.
Sign in
to read them.
Comments are read before they appear where anything in them needs a person to look.
Nothing posted here is ever deleted; a comment taken down keeps its text and the reason,
so the decision can be looked at again. How this works
