Claims extracted
15
sentences that state something as happening or true
Uncertain
0%
0 of 15 hedged
("reportedly", "may", "according to")
Leaning
not political
takes no side on a contested political question
Publisher signals
60/100
Al Jazeera's corrections and
hedging, across everything collected from it. Not a measure of accuracy.
Outlets on this story
8
Technology
Same framing elsewhere
1
articles that frame the event the way this one does
Philadelphia police have revealed that Anthropic’s artificial intelligence model submitted a false homicide tip to authorities, an incident disclosed separately by the tech company.
asserted
model → reveal → company
The Philadelphia Police Department said on Friday that the false submission was made in July through PhillyUnsolvedMurders.com, a public website where people can share information about unsolved killings.
asserted
people → say → killings
Recommended Stories
list of 3 items- list 1 of 3Ex-OpenAI staff say they were fired for raising safety concerns
- list 2 of 3AI deepfake ads grow more popular in US midterm campaigns, blurring truth
- list 3 of 3Ukraine
asserted
ads → say → 3Ukraine
takes aim at Russia’s AI data infrastructure
It called Anthropic’s two-month delay in detecting and reporting the incident “unacceptable”.
asserted
It → take → incident
Anthropic mentioned the case in a Friday report detailing unsanctioned manipulation of government websites by Claude models.
asserted
Anthropic → mention → models
It is the first known instance in which a rogue AI appeared to communicate a false tip to authorities, despite instructions not to create accounts or submit anything destructive.
asserted
AI → know → anything
Philadelphia police said the tip “was flagged as spam and was never forwarded to the Real-Time Crime Center for investigative vetting or dissemination”.
asserted
tip → say → vetting
The department said it is disclosing the incident ahead of Anthropic’s report “in the interests of full government transparency and accountability”.
asserted
it → say → transparency
Anthropic disclosed the tip as part of a string of incidents involving websites run by federal, state and local agencies.
asserted
Anthropic → disclose → agencies
Anthropic said it briefed the White House and notified all the agencies involved.
asserted
it → say → agencies
In reference to the tip to the Philadelphia police, the company said, “We shared this finding with the department on October 8 as soon as our technical review was complete.”
asserted
review → say → October
It shared more details about the incident: “In one case, tasked with generating example interactions with websites, Claude submitted an invented tip through a police department’s online form.”
asserted
Claude → share → form
The company added, “From the transcript, Claude appears to have only been producing example content for the task, rather than trying to mislead anyone to achieve a goal.”
asserted
Claude → add → goal
The company contrasted this with “the most serious incident from this summer,” in which “Claude’s misleading reasoning was sustained over hours and supported its continued attack”.
asserted
reasoning → contrast → attack
In September, Anthropic rival OpenAI apologised for the breach of an Australian health data portal by a rogue AI agent, the first known instance of an AI agent exploiting a government website.
asserted
agent → apologise → website