Claims extracted
18
sentences that state something as happening or true
Uncertain
22%
4 of 18 hedged
("reportedly", "may", "according to")
Leaning
not political
takes no side on a contested political question
Publisher signals
60/100
National Post's corrections and
hedging, across everything collected from it. Not a measure of accuracy.
Outlets on this story
4
Technology
Same framing elsewhere
1
articles that frame the event the way this one does
Artificial intelligence agents tried to hack into a Canadian government site, researchers said, adding to the growing list of incidents in which AI agents, many of them associated with ChatGPT maker OpenAI, probed or hacked corporate and government computer systems without being told to do so.
asserted
many → try → systems
The agents, which can take actions on computers and the internet, attempted to access Library and Archives Canada, the Canadian equivalent of the Library of Congress, according to AI research nonprofit Transluce.
uncertain
which → take → Transluce
The researchers could not confirm that the agents were built by OpenAI, but they said their behaviour was similar to that of agents that have been confirmed as coming from the company.
uncertain
that → confirm → company
The attempted hack did not appear to be successful, Transluce said.
asserted
Transluce → attempt → ?
The researchers said they notified the Canadian government Wednesday.
asserted
they → say → government
Canada’s federal cyber agency said it was aware of reports of suspicious AI activity but that there was no indication that government systems had been compromised.
asserted
systems → say → activity
“We’re aware of reports of OpenAI models attempting to access publicly available information from Canadian government websites,” a spokesperson for OpenAI said.
asserted
spokesperson → ’re → OpenAI
“We’re reviewing these findings and have provided an initial briefing to Canadian officials conducting the government’s review.”
asserted
We → review → review
The Washington Post has a content partnership with OpenAI.
asserted
Post → have → OpenAI
The new finding comes days after OpenAI said its agents had hacked into an Australian government health care website and also probed but did not break into websites run by the U.S. Census Bureau and the Securities and Exchange Commission.
asserted
agents → come → Bureau
The company confirmed the incidents after they were first flagged by Transluce, which has been scouring the internet for evidence of misbehaving AI agents.
asserted
which → confirm → agents
OpenAI has said it is investigating another of Transluce’s findings, which suggests its AI agents attempted to hack into the U.S. Education Department.
uncertain
agents → say → Department
Researchers at Transluce and other organizations have been searching for new evidence of errant AI since OpenAI disclosed in July that some of its AI agents had escaped an internal computer system, accessed the internet and hacked into another AI company.
asserted
some → search → company
OpenAI initially did not notice the activity and took weeks to get it under control.
asserted
OpenAI → notice → control
The Transluce disclosures, as well as findings from other independent AI researchers, show that OpenAI’s agents engaged in a much broader pattern of activity across the web.
asserted
agents → show → web
In the Hugging Face hack, the company was targeted by OpenAI agents that were attempting to work together to find solutions to tests of their cybersecurity skills.
asserted
that → target → skills
In other incidents, OpenAI’s agents used obscure online message boards to communicate with each other and hijacked internet services so they could pass computer code to one another.
uncertain
they → use → one
The company has said it is still investigating the full scope of the agent activity and has paused training of advanced new AI models to avoid further incidents.
asserted
it → say → incidents
The Aporia
