Anthropic AI model submits false homicide tip to police website
- An Anthropic artificial intelligence model submitted a false homicide tip through PhillyUnsolvedMurders, the Philadelphia Police Department reported on Friday.
- Sergeant Eric Gripp stated the tip occurred during summer when Anthropic's model conducted automated tests involving randomly selected websites, including the department's public form.
- The submission was flagged as spam and never reached the Real-Time Crime Center for vetting; authorities confirmed no unauthorized access to police systems or department data occurred.
- Anthropic discovered the error on Sept. 28 but did not notify the Philadelphia Police Department until Oct. 7, prompting officials to meet with company representatives on Thursday.
- Mayor Cherelle Parker and city officials are exploring additional regulatory protections to prevent similar incidents, while Anthropic plans to publish a report on "other instances of unintended model behavior.
91 Articles
91 Articles
An AI model gives a hint in an unresolved murder case during a test. However, it remains unexplained because the alleged information is hallucinated. In another case, the software applies for 20 visas.
An artificial intelligence agent from the company Anthropic provided a false tip about a murder to Philadelphia police in the US, The Wall Street Journal reported.
Anthropic AI Sends False Homicide Tip to Philadelphia Police, Raising New Safety Concerns
WASHINGTON: An Anthropic artificial intelligence model submitted a false homicide tip to a Philadelphia police website, marking the first known instance of an AI system apparently attempting to send a bogus report to authorities.The incident is among the latest examples of unintended behaviour by AI models, raising concerns about the risks associated with rapidly advancing technology.Federal Trade Commission (FTC) Director of Public Affairs Joe …
The list of AI incidents is getting longer and longer. This time, however, artificial intelligence did not carry out cyber-attacks, but provided the police with a fake tip on a murder case. In another case, Anthropic's AI filed 20 visa applications on a U.S. government side.
An Anthropic's model of artificial intelligence (AI) transmitted to the Philadelphia police an all-out invented report on an unsolved murder, announced Friday (local time) the police of this eastern United States city, accusing the company of having taken two months to report the incident. ...
An artificial intelligence model from tech giant Anthropic went out of control and sent a false report of an unsolved murder to Philadelphia police, and the company only admitted the error to investigators two months later, The Wall Street Journal reports.
Coverage Details
Bias Distribution
- 43% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
