Watermarking an LLM's output, in Kirchenbauer et al.

Watermarking an LLM's output, in Kirchenbauer et al., is basically turning token generation into a dynamic casino where the house secretly nudges the model toward green tokens. A z-test detector regenerates those context-dependent green sets and asks whether the generated text landed on them far more often than chance would plausibly explain. It isn't detecting “AI style”; it's detecting an intentionally planted statistical bias.