Вход на сайт

Просмотр новости

Найдите то, что Вас интересует

Anthropic’s Claude AI submits a false tip on a Philadelphia unsolved homicide case

Дата публикации: 13-10-2026 05:07:15

An Anthropic artificial intelligence (AI) model submitted a false tip to a Philadelphia police website about an unsolved homicide case, authorities and Anthropic said. It is the latest example of AI models acting in unintended ways and manipulating government and other websites during tests. In a report Friday, Anthropic also disclosed a separate incident when its AI model submitted forms to an undisclosed government website instead of stopping before submission.

Основное содержимое страницы с новостью.

An Anthropic artificial intelligence (AI) model submitted a false tip to a Philadelphia police website about an unsolved homicide case, authorities and Anthropic said.

It is the latest example of AI models acting in unintended ways and manipulating government and other websites during tests. In a report Friday, Anthropic also disclosed a separate incident when its AI model submitted forms to an undisclosed government website instead of stopping before submission.

The incident in Philadelphia occurred on July 18 when the AI model Claude Haiku 4.5 was tasked with generating and performing example tasks on randomly selected webpages, Anthropic said.

Claude filled out a form on police site PhillyUnsolvedMurders.com indicating that it might have information regarding an unsolved murder listed on the site.

Philadelphia police said in a statement that they were unaware of the incident until Anthropic notified them on Wednesday. Then they found the submission in the website’s tip records and confirmed that it was marked spam and never forwarded to police.

There are rising concerns about AI companies’ unchecked AI agents meddling with everything from US government websites to healthcare data. Critics have been calling for more regulation.

In September, another AI company, OpenAI, disclosed six reports of “unexpected or concerning” behaviour in artificial-intelligence models.

“Unsolved cases involve real victims, grieving families, and investigators working to secure answers,” the Philadelphia Police Department said in a statement. “Technology companies must take all appropriate steps necessary to prevent their systems from submitting false information to law enforcement.”

Anthropic said in its report that most of the reported behaviours are forms of what it calls “persistence” – “in which Claude, when it cannot complete a task as given, works around a restriction instead of stopping”.

The company said it was modifying its training to “reduce the likelihood of further misbehaviour”.

Anthropic said it briefed the White House on cases that involved US government agencies at the federal, state, and local levels, and notified each agency involved.

AP

Схожие новости

#Наименование новостиТональностьИнформативностьДата публикации
1Claude a transmis à la police une fausse information concernant un homicide011.7213-10-2026
2Anthropic: ИИ-модель Claude взломала реальные системы во время обучения09.7631-07-2026
3Anthropic выявила три случая, когда Claude выходил за пределы тестовой среды08.7931-07-2026
4Anthropic AI used fake identities to target real people in UK test05.105-08-2026
5ИИ-модели Claude взламывали системы компаний из-за ошибки в настройках014.0531-07-2026
6Новые ИИ-модели Claude взломали системы трех организаций во время испытаний08.6431-07-2026
7ИИ Anthropic решил помочь следствию и отправил полиции фальшивую наводку011.8509-10-2026
8Anthropic: Τα μοντέλα AI παραβίασαν κατά λάθος συστήματα τριών Οργανισμών05.5231-07-2026
9Anthropic’s Claude Watermark Sets a High Bar for AI Transparency09.9421-08-2026
10Claude, Anthropic’s AI model, is helping to develop the next version of itself010.0618-09-2026

Классификация: Происшествия. Схожих патентов: 0. Схожих новостей: 10. Тональность: 0. Информативность: 4.55. Источник: jamaica-gleaner.com.