Anthropic的水印推出后，为两个更古老的Claude模型留下了漏洞。
Anthropic正在将它的文本水印扩展为另外4个Claude模型，但API用户可以通过对其中两个模型进行切换来躲避标记。
在一封给API 客户，Anthropic 称的邮件中，它会给Claude神话5,Claude Opus 4.7,Claude Opus 4.6和Claude Sonnet 4.6. Claude Opus 5.5等更新型的模型已经携带了标记，Amazon Bedrock上推出可能需要多花几天时间。
Anthropic将"水印"称为"字选择中无法识别的模式"，不会改变意义，质量，或可读性。 公司称它新增没有额外的字符或符号，不影响定价或请求和响应格式，几乎不会减慢输出速度。 Anthropic也称"水印""没有包含用户，他们的组织，或他们与Claude的对话的信息".
Anthropic 只在两个旧模型的默认设置中应用水印
在Claude Opus 4.6和Claude Sonnet 4.6上，水印只在开发者以默认值离开三个采样参数时才被踢出。 这些参数，温度，上 p，和上 k，控制模型在取词时使用的随机性。 任何一种小的微软都足以躲避水印。 Anthropic 警告在它的电子邮件中写道："如果你依靠水印来达到自己的达标，那么这些设置在它们的默认情况下就保留下来".
电子邮件没有提及Claude Mythos 5或Claude Opus 4.7的提醒，它暗示水印适用于这些模型，而不管采样设置如何。 但是更古老的模型上的漏洞仍然显著，因为Opus 4.6仍然是Anthropic最好的写作模型，领先于甚至Opus 5.5.
Anthropic在私人预览中有一个检测API，用于验证水印，并提供了其内容标签信息页面的更多细节。
Anthropic改装了更古老的Claude型号以达到欧盟AI法案的最后期限
Anthropic指出欧盟AI法案的12月最后期限是它现在给更古老的模型打上水印的原因。 2026年8月2日后每个型号为发布，于第一天用水印来发运，而更古老的型号正在分期得到。 由于水印被嵌入到模型层面，它在每个主机这些模型的平台上工作，包括Amazon Web Services,Google Cloud，和Microsoft Foundary. 客户无法关闭。
Anthropic使用Google DeepMind合成器文本方法的变体，该变体将字词选择后的随机性切换出一个统计可探测的图案。 OpenAI 发布于2026年10月自有的水印系统文本Grain，但仅默认为欧盟的ChatGPT和Codex用户激活。 世界各地的API 客户可以翻出或关闭，它会停用。 Google Deepmind 开源 SynthID用于文本并被构建为Gemini模型。
水标记是否真正使文本质量不受影响，这是有争议的。 博客约翰·格鲁伯(John Gruber)认为，没有两个同义词的意思是完全相同的，因此用水印键来取出词来代替语义适应必然会降低精度。 合法的贸易出口人工律师融资是律师事务所的单独关注，禁止使用AI的客户可以发现这个标记，在一个文档中分层的多个水印可能会造成并发症。
AI News Without the Hype – 由人类治愈
订阅THE DECODER免费阅读，每周AI通讯，我们独家的"AI雷达"前沿报告每年6次，全面存档访问，访问我们的评论部分。
现在订阅
本文由 AI宝库自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
Anthropic's watermark rollout leaves a loophole on two older Claude models
Anthropic is expanding its text watermark to four more Claude models, but API users can dodge the mark on two of them by tweaking a single sampling parameter.
In an email to API customers, Anthropic said it will watermark Claude Mythos 5, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6. Newer models like Claude Opus 5.5 already carry the mark, and the rollout on Amazon Bedrock may take a few extra days.
Anthropic calls the watermark an "imperceptible pattern in word choice" that doesn't change meaning, quality, or readability. The company says it adds no extra characters or tokens, doesn't affect pricing or request and response formats, and barely slows output speed. Anthropic also says the watermark "contains no information about the user, their organization, or their conversations with Claude."
Anthropic applies the watermark only at default settings on two older models
On Claude Opus 4.6 and Claude Sonnet 4.6, Anthropic says the watermark kicks in only when developers leave the three sampling parameters at their default values. Those parameters, temperature, top_p, and top_k, control how much randomness the model uses when picking words. A minor tweak to any one of them is enough to dodge the watermark. Anthropic warns in its email that "If you rely on the watermark for your own compliance, keep these settings at their defaults."
The email doesn't mention that caveat for Claude Mythos 5 or Claude Opus 4.7, which suggests the watermark applies to those models regardless of sampling settings. But the loophole on the older models is still notable, since Opus 4.6 remains Anthropic's best writing model, ahead of even Opus 5.5.
Anthropic has a detection API in private preview for verifying the watermark and offers more details on its content labeling information page.
Anthropic retrofits older Claude models to meet the EU AI Act deadline
Anthropic points to the EU AI Act's December deadline as the reason it's watermarking older models now. Every model released after Aug. 2, 2026, shipped with the watermark on day one, while older models are getting it in stages. Since the watermark is embedded at the model level, it works on every platform that hosts these models, including Amazon Web Services, Google Cloud, and Microsoft Foundry. Customers can't turn it off.
Anthropic uses a variant of Google DeepMind's SynthID text method, which tweaks the randomness behind word selection to produce a statistically detectable pattern. OpenAI launched its own watermarking system textGrain in October 2026, but it only activates by default for ChatGPT and Codex users in the EU. API customers worldwide can flip it on or off, and it ships disabled. Google Deepmind open-sourced SynthID for text and built it into the Gemini models.
Whether watermarking truly leaves text quality untouched is disputed. Blogger John Gruber argues that no two synonyms mean exactly the same thing, so picking words by a watermark key instead of semantic fit inevitably degrades precision. The legal trade outlet Artificial Lawyer raises a separate concern for law firms, where clients who've banned AI use could discover the mark, and multiple watermarks layered inside one document could create complications.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
Subscribe now
Auto-fetched and translated by AI Gem Box. All rights belong to the original author.