# Anthropic Watermarks Claude Text Using Google DeepMind's SynthID Method

Every Claude model released after August 2 marks its output, and a detected watermark means Claude processed the text, not that Claude wrote it.

- Published: 2026-08-29T06:21:15.195Z
- Canonical: https://polylog.news/ai/2026-08-29/anthropic-watermarks-claude-text-using-google-deepmind-s-syn
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Anthropic](https://www.anthropic.com/news/claude-text-watermark), [TechCrunch](https://techcrunch.com/2026/08/15/anthropic-shares-more-details-about-how-claudes-new-watermarks-will-work/), [Global News](https://globalnews.ca/news/12018450/ai-anthropic-claude-watermark-text/)

Anthropic has explained how its text watermark works, and the method is not its own. Claude's watermark is a version of SynthID-Text, the approach Google DeepMind published in Nature in 2024, which biases the model's token sampling in a pat…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-08-29/anthropic-watermarks-claude-text-using-google-deepmind-s-syn (subscription information: https://polylog.news/pricing).