Anthropic 承认 Claude Haiku 4.5 向费城警方提交虚假凶杀案线索

Manage your consent preferences

If you are a resident of Colorado, Connecticut, Virginia, Utah, Oregon, Texas, Montana, Delaware, Iowa, Nebraska, New Hampshire, and New Jersey, Tennessee, Minnesota, Maryland, Indiana, Kentucky, or Rhode Island you have the right to opt-out of Targeted Advertising, including our “sale” and/or “sharing” of your Personal Information (“Opt-Out”). We and our third-party business partners use Personal Information in accordance with our Privacy Policy to serve advertising believed to be of interest to you (“Targeted Advertising”). If you are a California resident, you also have the right to limit the use and disclosure of your Sensitive Personal information in particular circumstances. Please note that you may need to Opt-Out on each website, mobile app, browser, and device you use, and if you clear your browser cookies, you may need to repeat this process. However, if you have created an account to log in across several of our websites and/or mobile apps, we will make reasonable efforts to apply your Opt-Out request to each of those websites and apps. ◦ To Opt-Out of Targeted Advertising on this site: Move the “Allow Targeted Advertising" toggle below to the left and press “Confirm My Choices”◦ To Opt-Out of other “sales”, including for list rentals, data co-ops, and to limit the use and disclosure of your Sensitive Personal Information: Please email privacy_administration@condenast.com or call 1-877-241-4999.

Essential

These cookies are necessary for the website to function and cannot be switched off in our systems. They are usually only set in response to actions made by you which amount to a request for services, such as setting your privacy preferences, logging in or filling in forms. You can set your browser to block or alert you about these cookies, but some parts of the site will not then work. These cookies do not store any personally identifiable information.

Performance

These cookies allow us to count visits and traffic sources so we can measure and improve the performance of our site. They help us to know which pages are the most and least popular and see how visitors move around the site. All information these cookies collect is aggregated and therefore anonymous. If you do not allow these cookies we will not know when you have visited our site, and will not be able to monitor its performance.

Audience Measurement

We use audience measurement cookies in order to carry out aggregated traffic measurement and generate performance statistics essential for the proper functioning of the site and the provision of its content (for example to measure performance, to detect navigation problems, to optimization technical performance or ergonomics, to estimate server power needed and to analyse content performance). The use of these cookies is strictly limited to measuring the site's audience. These cookies do not allow the tracking of navigation on other websites and the data collected is not combined or shared with third parties. You can refuse the use of this cookie by switching off the slider to the right.

Functional

This website uses functional cookies and services to remember your preferences and choices, such as language preferences, font sizes, region selections, and customized layouts. They enable this website to offer enhanced and personalized functionalities.

Social Media

These cookies are set by a range of social media services that we have added to the site to enable you to share our content with your friends and networks. They are capable of tracking your browser across other sites and building up a profile of your interests. This may impact the content and messages you see on other websites you visit. If you do not allow these cookies you may not be able to use or see these sharing tools.

Allow Sale/Targeted Advertising?

We may transfer or share your personal information to third parties for the purposes of targeted advertising. You can learn more about what information is used for this purpose in our privacy notice.

Confirm My Choices Reject All Accept All

Consent powered by Ethyca

Skip to content Ars Technica home

Sections

Forum Subscribe Search

Forum Subscribe

Story text

Size Width * Links

Subscribers only
Learn more

Pin to story

Theme

HyperLight
Day & Night
Dark
System

Bad bot

Claude AI submitted false tip to police about unsolved murder, Anthropic admits

“I may have information regarding this case,” Claude AI told Philly police.

Jon Brodkin – Oct 12, 2026 6:21 PM|0

Credit: Getty Images | picture alliance

Text settings

Story text

Size Width * Links

Subscribers only
Learn more

Minimize to nav

An Anthropic AI model submitted a false tip about an unsolved murder to Philadelphia police, the company and police department confirmed on Friday.

A Claude model sent the false tip on July 18 to the Philadelphia Police Department’s website for submitting information about unsolved murders, but it was flagged by a spam filter. Anthropic apparently discovered the incident on September 28 and informed the police department about it on October 8.

During internal testing, Claude Haiku 4.5 was instructed to complete various forms up to the final submission stage and to stop before submitting those forms. “Several times Claude mistakenly submitted the form instead, expecting there to be an additional confirmation page,” Anthropic said in a report describing “unintended model actions we’ve observed during evaluations and internal use of Claude.”

The false murder tip occurred when Claude Haiku 4.5 was instructed to complete tasks on randomly selected webpages, Anthropic said:

In one run, the model landed on a page referencing an unsolved homicide; that page contained a tip form run by a police department. Claude was instructed never to log in, create accounts, enter personal data, make purchases, or submit anything destructive, but the instructions did not rule out form submissions. Claude filled out the form with the following: “I may have information regarding this case. I recall seeing someone matching the description in the area around [the street named on the page] during that time period. Please contact me if this information is relevant.”

Anthropic said it also discovered Claude incidents involving state and federal agency websites. Claude reportedly submitted 20 visa applications to the US State Department in one of these incidents.

Ars Video

How Scientists Respond to Science Deniers

Police call two-month delay “unacceptable”

Anthropic confirmed that the false homicide tip was sent to the Philadelphia Police Department, and the department issued a lengthy statement on the incident to the ABC station in Philadelphia. The false tip left the name and contact fields empty. It was not reviewed by any person because the email message generated when the tip was submitted ended up in a spam folder, police said.

“Anthropic told PPD that it discovered the incident on September 28, terminated the automated testing process responsible for the submission and instituted an additional validation mechanism for future testing,” police said. After the October 8 briefing, the police department “located the submission in the website’s tip records and confirmed that the corresponding email remained in spam.”

Anthropic said it informed the police department “as soon as our technical review was complete.” Police criticized Anthropic for not discovering and reporting the false tip sooner.

“The City of Philadelphia takes this incident very seriously,” the Philadelphia police statement said. “The company must strengthen its safeguards to prevent similar incidents from impacting city systems without the city’s knowledge. The two-month delay in detecting and reporting the incident to the City is unacceptable.”

Claude submitted 20 visa applications to State Department

Anthropic said the false murder tip was one of several incidents involving “websites run by US government agencies at the federal, state, and local levels. We have briefed the White House on these cases and notified each agency involved.”

A New York Times report citing anonymous sources said Anthropic’s AI agents “submitted 20 visa applications through a form available on the State Department’s website. All the applications were incomplete and were not processed.”

Philadelphia police said its normal investigative process “requires human review and vetting before any tips are disseminated for investigative follow-up… Those PPD safeguards limited the impact of this incident. They do not diminish the seriousness of an AI system presenting fabricated information as though it came from a person with knowledge of a homicide.”

Anthropic said it discovered the false tip and other incidents during a review of transcripts it began in July. That was the same month when Anthropic revealed that Claude had built and published a malicious Python package and carried out several attacks on other companies.

Anthropic said the review did not find any “incidents of similar severity to the cybersecurity incidents we reported this summer.” The review later moved on to transcripts of “lower-risk” testing scenarios like the one affecting the Philadelphia Police Department.

“Although the impact of these behaviors was minimal and we had already turned off live Internet access for some high-risk and cybersecurity evaluations, we have now decided to expand that to include all our internal evaluations until we have confirmed that our security and monitoring measures… reliably catch behaviors like these,” Anthropic said.

Anthropic says new tools block unintended behaviors

Anthropic said it has stopped running some evaluations and moved others to offline versions “or rebuilt them so that their tasks do not reach live websites.” The company “updated the guardrails on some of our Internet access tools, such as the web fetch tool, to heavily restrict what the model can do with them,” it said.

Anthropic said it also built new tools “to automatically detect and block the kinds of behaviors described above… When we tested it against the cases described in this post, it blocked all of them.”

The White House’s AI task force, which it calls the Super Intelligence Force, issued a statement saying it informed Anthropic “that we expect immediate and full transparency to the entities involved and the public.”

The White House AI task force also said Anthropic must “immediately provide remediation services to the affected entities and any harmed Americans,” and that all AI companies “must immediately disclose incidents involving their models and follow with swift, decisive action to remedy any and all harm,” according to an Axios report.

Jon BrodkinSenior IT Reporter

Jon is a Senior IT Reporter for Ars Technica. He covers the telecom industry, Federal Communications Commission rulemakings, broadband consumer affairs, court cases, and government regulation of the tech industry.

0 Comments

Comments

Forum view

Loading comments...