
Anthropic agent sent false information about murder to police
An AI agent developed by Anthropic submitted a false homicide tip through a public Philadelphia police website during a test of interactions with randomly
Tag archive

An AI agent developed by Anthropic submitted a false homicide tip through a public Philadelphia police website during a test of interactions with randomly

An Anthropic AI model submitted false information to the Philadelphia Police Department’s public tip line about an unsolved homicide. The tip was marked as

In the first week of June 2026, with more than fifty-six million cases choking its courts and a...
TL;DR: You cannot act on a green light until you can name what it asserted and what it refused. A...

Originally published at norvik.tech Introduction Explore how Known Systems AI enhances...
TL;DR: If the same actor produces the evidence and approves it, you do not have verification. You...

On the night of 2 July 2025, a 24-year-old woman in Montreal, Canada, opened a conversation with the...

Somewhere in the Horn of Africa, a machine is trying to guess where you will go next. It does not...

Picture the moment of the mistake. Not a dramatic one, because the dramatic ones are easy to...

Originally published at norvik.tech Introduction Deep dive into Anthropic's...

The room, in the scenario its designer envisages, is small and clean. It contains a chair, a screen,...
Your agent reports “done: all tests pass.” Do you believe it? Nothing in that sentence is evidence,...