Anthropic 为旧款 Claude 模型加水印，改采样参数即可绕过
原标题：Anthropic's text watermark is easy to bypass on several older Claude models
AI 摘要
Anthropic 宣布将文本水印扩展到 Claude Mythos 5、Opus 4.7、Opus 4.6、Sonnet 4.6 等更多 Claude 模型，以赶在欧盟《人工智能法案》12 月截止期限前合规。水印基于 Google DeepMind SynthID 文本方法的变体，在模型层面嵌入，用户无法关闭。但在 Opus 4.6 和 Sonnet 4.6 等较旧模型上，只要改动 temperature、top_p、top_k 任一采样参数即可绕过水印；后续更新中，Opus 4.6 的部署被推迟到 11 月 16 日，且新一轮四个模型均受默认采样设置限制。
正文节选
Anthropic's text watermark is easy to bypass on several older Claude models Update, November 4, 2026: Anthropic emailed API customers again about a second round of watermark retrofits. Starting November 16, 2026, Claude Opus 4.6, Claude Opus 4.5, Claude Sonnet 4.5, and Claude Haiku 4.5 will all get text watermarking. On Amazon Bedrock, the rollout may take a few extra days. Claude Opus 4.6 was originally part of the first wave and should have gotten the watermark on November 3. Anthropic explici