Anthropic 详解 Claude 文本水印技术：符合欧盟 AI 法案，不影响输出质量

AI 摘要

Anthropic 宣布未来 Claude 模型将内置文本水印，以符合欧盟 AI 法案要求。该水印基于 Google DeepMind 的 SynthID-Text 方法，通过改变模型选择词语时的随机性来源来嵌入模式，不影响输出质量、可读性或成本，且不携带个人或组织信息。Anthropic 表示，水印对读者不可见，但可通过密钥检测文本是否由 Claude 生成。

正文节选

How Claude’s text watermark works Future Claude models will generate text that contains a watermark. This is a way of determining the likelihood that Claude was involved in writing the text, and we, along with several other major AI providers, are implementing this change to comply with the EU AI Act. In this article, we share answers to some of the questions we’ve received about how our chosen watermarking method works, whether it affects Claude’s outputs, and why we’re making this change. To s

发布时间：—

抓取时间：2026-08-15 03:25

来源机构：Anthropic