AI watermarking: a green/red token bias seeded by the prior word, a z-test detector, and why paraphrasing breaks it

Article automatically generated from technical news.

The question I keep getting asked is "how do you prove a piece of text was written by a machine — without access to the machine?" AI watermarking is the surprisingly clever answer, and once I understood the trick I had to build it to believe it. The generator hides a signal in its output on purpose; a detector that knows only the rule (not the model, not any weights) reads it back with a confident statistical verdict. I built a demo where the green-list seeding, the green fraction, t