# Anthropic Details a Text Watermark That Biases Claude's Word Choices Without Changing Output Quality

The method adds no hidden characters and no extra tokens, and a detected mark means text passed through Claude, not that Claude wrote it.

- Published: 2026-09-06T06:32:46.692Z
- Canonical: https://polylog.news/ai/2026-09-06/anthropic-details-a-text-watermark-that-biases-claude-s-word
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Anthropic News](https://www.anthropic.com/news/claude-text-watermark)

Anthropic published an explanation of how Claude's text watermark works after developers asked what it does to outputs. The mechanism is a keyed bias over token selection. Among the highest-scoring candidate tokens at each step, a key influ…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-06/anthropic-details-a-text-watermark-that-biases-claude-s-word (subscription information: https://polylog.news/pricing).