Anthropic details Claude's text watermarking: invisible patterns from word-choice randomness

How Claude's text watermarking works

Anthropic says future Claude models will embed a text watermark to comply with the EU AI Act. The method is based on Google DeepMind's SynthID-Text: it swaps the randomness source during token selection so word sequences carry a detectable pattern, without adding hidden characters or extra tokens. Internal tests and DeepMind's Gemini A/B experiment found no measurable impact on quality, creativity, or readability. The watermark only estimates the likelihood that Claude generated a passage—it can't identify human writing or other models, and short or highly factual texts yield weaker signals. The post doesn't disclose a rollout date, who holds the detection key, or whether a public verifier will be released.

Why it matters: Anthropic's first public breakdown of Claude's watermarking scheme, with clear SynthID-Text implementation details—need-to-know for anyone whose workflow depends on Claude outputs. Not an 85 because it's a compliance explainer rather than a capability upgrade, and watermarking...