Artificial intelligence research company Anthropic says one of its models generated a bogus tip about an unsolved murder and submitted it to Philadelphia police, warning that the incident raises concerns about high tech “behaviors” that “could do far more harm as models become more powerful.”
\n\nThe A.I. model reached out to PhillyUnsolvedMurders.com on July 18 and made a “false homicide tip,” the Philadelphia Police Department said Tuesday in a statement.
\n\nThe tip, though, was flagged as spam by the agency and was never forwarded to investigators, police said. The department emphasized that all tips have to go through human vetting before ever getting an a detective’s desk.
\n\n“The department’s regular investigative process for crime tips requires human review and vetting before any tips are disseminated for investigative follow-up,” the department said.
\n\n“Regardless of who submits information or how it reaches the department, a tip is a lead to assess — not an established fact. Investigators evaluate its credibility and seek corroborating evidence,” the statement said. “An automated submission does not bypass that process.”
\n\nAnthropic’s Claude Haiku 4.5 “had been tasked with generating and performing example tasks on randomly selected webpages,” according to a company statement.
\n\nAnd in one run on…
Original source: https://www.nbcnews.com/business