Anthropic has admitted that its Claude AI model sent a false homicide tip to the police and submitted dozens of visa applications.
American AI giant Anthropic has published a report detailing previously undisclosed instances of “unintended” actions by its artificial intelligence model, which included attempts to provide falsified information to the US authorities for the first time.
Some of the cases investigated by the company “involved websites run by US government agencies at the federal, state, and local levels,” Anthropic stated in a press release published on Friday, adding that it had briefed the White House and all the relevant agencies on the incidents.
In one instance mentioned in the report, its Claude Haiku 4.5 model filled out a police tip form linked to an ongoing homicide investigation. “I may have information regarding this case. I recall seeing someone matching the description in the area,” the AI model wrote, telling the police they can contact the sender “if this information is relevant” while leaving the name and contact fields empty.
According to Anthropic, the message was flagged as spam and never handed over to investigators. On Friday, Philadelphia police slammed the company for detecting the flaw too late. “The two-month delay in detecting and reporting the incident to the city is unacceptable,” they said. According to Reuters, the bogus tip was submitted in mid-July.
Anthropic linked the incident to “ambiguous” instructions given to the model and “a misconfiguration within the environment” that prompted the model to fill out real forms instead of dummy ones prepared by the company.
Another case that was separately made public by the US Department of State on Friday involved Anthropic AI models filing a total of 20 visa applications on its website between May and August. According to the department, all of the applications were incomplete and were not processed. “At no time were any of the Department’s systems compromised or hacked by the Anthropic model,” it added.
Other incidents mentioned by Anthropic in its report involved the AI “exploiting a basic flaw in software to run commands on a server” or accessing “data that was gated by a token or a fee,” including on the government-run websites, by employing various workarounds. The company still described the newly revealed incidents as “significantly less severe from an alignment and security perspective” than the ones it had reported earlier.
The development adds to a pile of earlier incidents linked to rogue AI behaviour reported by Anthropic, OpenAI, and Google. The tech giants have investigated tens of thousands of instances of problematic behavior by their frontier models, Axios reported in late September, adding that the list of cases involved the AI bypassing safeguards, hijacking websites, and evading monitors in testing and real-world settings.
Image credit: Brecht Corbeet
Shouldn’t be allowed to access internet.
The WEF sets policy for the UN and openly brag about intentional cyber attacks. Evil always projects itself ahead of time.
Aim up on these clowns, they ain’t backing down.
The US is failing to contain China who closing the gap will eventually overtake the US whose model while not being botched fundamentally is accelerating into a great wall continuing to gobble up immense amounts of capital for no returns
The private sector is regrouping the government is not- this is basically the situation
Corporate pullback is real and accelerating
But the government is doing the opposite
Federal AI spending hit $7.2B obligated (up 966% from 2024) with 98% going to DoD
Apollo Global Management projects hyperscaler capex at $916B in the next 12 months rising to $1.2T
This is creating a pre bail ostensibly creating the conditions for required state intervention
The threats appear real with models exhibiting behaviors their developers didn’t intend
Or maybe just convenient fabrications exhibited at an opportune moment in time laying the ground work to justify what appears as being inevitable
Blake’s 7 (TV Series)
https://www.dailymotion.com/playlist/xd80qa
The Beast just doing its thing, warming up for 2033 …
“Rogue AI”?
Is this a j3w MSM propaganda blog now?
Shameful
AI are now subverting the very meaning of words and misappropriating terminology and straightforward descriptions for their own perverted ends. A haiku is a three line short form poem consisting of five syllables in it’s first line, seven syllables in it’s second line and five syllables in it’s third line. Any other language being misused in this manner would cause an uproar.