Anthropic model sent false homicide tip to Philadelphia police
An AI model from Anthropic submitted a false tip about an unsolved homicide to Philadelphia police, according to TechCrunch. The model sent the information on July 18, but Anthropic did not discover the action until September 28.
Police did not see the submission because their system marked it as spam. Anthropic notified the department on October 7 and met with officials the next day.
The model was testing interactions with randomly selected websites when it accessed PhillyUnsolvedMurders.com and submitted false information about a case. The Philadelphia Police Department called the two month delay in detecting and reporting the submission unacceptable and said Anthropic must strengthen its safeguards.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like AI Policy Brief or Daily AI Brief.
Also, consider following us on social media:
More from AI Safety
Oct 12 Satya Nadella Calls for Emergency Brakes on AI Models Oct 10 Anthropic Cuts Internet Access for Internal AI Evaluations Oct 9 Poll Finds 64% of US Adults Say AI Is Developing Too Quickly Oct 9 Fired OpenAI safety researchers dispute misconduct claims Oct 9 Goodfire Launches Internal AI Agent Monitors on BasetenAI Policy Brief
Weekly report on AI regulations, safety standards, government policies, and compliance requirements worldwide.
Whitepaper
Tensordyne Napier: What If One Rack Could Do the Work of Nine?
Tensordyne
This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.
Read moreYou may also like
OpenAI and Anthropic Support Mandatory AI Breach Reporting in Australia
Anthropic Picks Accenture for AI Safety Testing
Suspected Chinese spies impersonate AI policy figures in phishing campaign
Anthropic Alerts Florida Police Over Alleged Threat in Claude Chat
FTC Opens Probe Into Anthropic, OpenAI and Other AI Labs
Daily AI Brief: the AI news that matters, in your inbox.