How AI text watermarking really works

Five explainers on the mechanics: what a watermark actually is, what detectors measure, what editing does to the statistics, and which providers have deployed anything. Written to be accurate rather than reassuring.

• What Is an AI Text Watermark?

  An AI text watermark is a statistical bias built into a model's word choices. Here is how the green-list method works, what a detector actually measures, and why you cannot see it by reading.

  7 min read

• How AI Text Detectors Actually Work

  Watermark detectors, perplexity classifiers and stylometry work in completely different ways. Here is what each one measures, which are reliable, and why false positives fall hardest on non-native writers.

  8 min read

• Does Paraphrasing Remove an AI Watermark?

  Paraphrasing weakens statistical watermarks — the research says so plainly — but the effect depends on how much you change and how long the text is. Here is the honest answer.

  7 min read

• AI Text Watermarking by Model: Who Actually Does It

  Google's SynthID-Text is the only production text watermark at scale. OpenAI built one and never shipped it; Anthropic has not deployed one. A provider-by-provider status check.

  6 min read

• Writing With AI Without Misrepresenting Authorship

  Where the real line sits between using a tool and claiming credit you have not earned, how to keep evidence of your own process, and what to do if you are wrongly accused.

  7 min read