Skip to content
Ahead of AI (Sebastian Raschka)· Sebastian Raschka, PhD·AI score58

Raschka explains how Claude's text watermarking works

How Claude Watermarks AI-Generated Text

Summary

Sebastian Raschka published a 48-minute lecture explaining Anthropic's Claude text watermarking. The watermark is applied at the sampling stage, not inside the model, using a secret key to derive a random seed that makes some token choices deterministic. Detection uses SynthID-Text-style tournament sampling and scoring functions, avoiding rerunning the LLM, but requires the key.

This site provides summaries and links to the originals only.

Source: Ahead of AI (Sebastian Raschka) · magazine.sebastianraschka.com