How Claude's text watermarking works
Original title:How Claude’s text watermark works
AI summary
Future text generated by Claude models will contain watermarks to indicate the likelihood that the text was written by Claude, a change Anthropic is implementing to comply with the EU AI Act. The method is based on Google DeepMind's SynthID-Text technology and has no practical impact on output quality, creativity, or readability. Readers cannot distinguish watermarked text from ordinary text, and it adds no extra tokens or cost.
Key Takeaways
- Future text generated by Claude models will contain watermarks to indicate the likelihood that the…
- The method is based on Google DeepMind's SynthID-Text technology and has no practical impact on…
- Readers cannot distinguish watermarked text from ordinary text,and it adds no extra tokens or cost.
Quick Facts
- Published
- Updated
- Source
- Anthropic:Newsroom(网页)
- Category
- Industry
- AI score
- 65
SynthID-Text 只改变等概率候选词的随机来源,不影响生成质量,却能用密钥校验文本与 Claude 的关联概率,为内容溯源提供了一种非侵入式检测思路。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: How Claude's text watermarking works. August 14, 2026. https://new.nat6.net/en/news/cmstc3u8j02xhro0xf5o1ouas/