#google-deepmind

Anthropic's own explainer on its Claude text watermark, a version of Google DeepMind's SynthID-Text: it doesn't add hidden characters but instead uses a key plus preceding context to bias which random number settles low-stakes word choices, leaving a pattern detectable only to someone with the key. Covers why it doesn't affect output quality, why it's sparser on factual text and code, why it's implemented across major AI providers under the EU AI Act, and its detection limitations.

Linear Digressions breaks down the mechanism behind Anthropic's Claude text watermark, based on Google DeepMind's SynthID Text (Nature, 2024): rather than tagging output or hiding invisible characters, it biases token-by-token sampling via a tournament-style selection driven by random functions seeded from a private key, leaving a statistical signature that accumulates over many tokens without changing the overall output distribution. Also covers why detection reliability depends on text length and entropy, and how heavy editing weakens the signal.

via Understanding AI Text Watermarking