# Anthropic says text watermarking scheme relies on inconsequential words

- URL: https://talkfuse.com/story/anthropic-says-text-watermarking-scheme-relies-on-inconsequential-words/
- Published: 2026-08-15T00:44:41+00:00
- Updated: 2026-08-15T01:48:16+00:00
- Original publisher: The Register
- Original article: https://www.theregister.com/ai-and-ml/2026/08/15/anthropic-says-text-watermarking-scheme-relies-on-inconsequential-words/5288156
- Topics: AI, Technology

## Key points

- Anthropic plans detectable watermarks for Claude-generated text.
- It alters low-stakes wording without changing intended meaning.
- Factual content and code receive limited or no watermarking.

## Summary

Anthropic has announced a plan to watermark text produced by its Claude AI models, partly to help comply with the EU AI Act and make AI-generated material more detectable. The scheme subtly steers the model towards alternative but inconsequential word choices, creating a statistical signature that can later be identified with a digital key.

The method draws on Google DeepMind’s SynthID-Text research and is intended to preserve meaning, creativity and readability; Anthropic says internal testing and human evaluations found no quality difference. It would be used more sparingly in factual writing, where wording changes could reduce accuracy, and is unsuitable for consequential text or code where swapping terms could alter meaning or function.

---
Summarised by TalkFuse (https://talkfuse.com/). Quote the original publisher for the reporting and link this page for the summary and discussion.