PulseAugur
中
实时 20:35:31
English(EN) Anthropic's watermark rollout leaves a loophole on two older Claude models

Anthropic 扩展 Claude 文本水印功能，但旧款模型存在漏洞 · 跟踪 3 个来源

作者 PulseAugur 编辑部 · [5 个来源] ·

Anthropic 正在将其文本水印系统扩展到另外四款 Claude 模型，包括 Claude Mythos 5、Opus 4.7、Opus 4.6 和 Sonnet 4.6，以符合欧盟人工智能法案。虽然较新模型已具备此功能，但旧款模型正在更新，以在词语选择中嵌入不可见的统计模式。然而，Claude Opus 4.6 和 Sonnet 4.6 上存在一个漏洞，通过更改单个采样参数即可绕过水印，Anthropic 已就此向用户发出警告。 AI

影响 提高人工智能生成内容的追溯性以符合监管要求，尽管旧款模型上的参数漏洞限制了其当前的严密性。

排序理由 关键人工智能透明度功能在多个模型上的扩展，并存在一个已知的技术漏洞。

在 The Decoder 阅读 →

AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →

Anthropic 扩展 Claude 文本水印功能，但旧款模型存在漏洞 · 跟踪 3 个来源

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
关键人工智能透明度功能在多个模型上的扩展，并存在一个已知的技术漏洞。
Source corroboration
5 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
policy, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
10 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+2 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [5]

  1. The Decoder TIER_1 English(EN) · Matthias Bastian ·

    Anthropic的文本水印在多个旧款Claude模型上易于绕过

    <p><img alt="" class="attachment-full size-full wp-post-image" height="768" src="https://the-decoder.com/wp-content/uploads/2026/08/Claude-Watermark.png" style="height: auto; margin-bottom: 10px;" width="1376" /></p> <p> Anthropic is rolling out text watermarks to four more Claud…

  2. The Decoder TIER_1 English(EN) · Matthias Bastian ·

    Anthropic 的水印推出为两款旧款 Claude 模型留下了漏洞

    <p><img alt="" class="attachment-full size-full wp-post-image" height="768" src="https://the-decoder.com/wp-content/uploads/2026/08/Claude-Watermark.png" style="height: auto; margin-bottom: 10px;" width="1376" /></p> <p> Anthropic is expanding its text watermark to four more Clau…

  3. dev.to — LLM tag TIER_1 English(EN) · News ·

    Anthropic 从11月3日起为四款旧款Claude模型启用隐形水印

    <p><a class="article-body-image-wrapper" href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fcdn.bsky.app%2Fimg%2Ffeed_fullsize%2Fplain%2Fdid%3Aplc%3Azl7pjaqajbk5mlwalj62hiz2%2Fbafkreiditauhudat6c634a3pluzdqn2s…

  4. dev.to — LLM tag TIER_1 English(EN) · Rohan Tech official ·

    Anthropic 为 Claude 的文本添加水印：这对你意味着什么

    <p>If you use Claude, some of what it writes for you now carries a hidden signature. Anthropic has started embedding an invisible watermark in Claude's text — and from Tuesday, November 3, the mark reaches four older models: Claude Mythos 5, Opus 4.7, Opus 4.6, and Sonnet 4.6.</p…

  5. dev.to — LLM tag TIER_1 English(EN) · News ·

    Anthropic将Claude文本水印扩展到另外4个模型，其中两个存在参数漏洞

    <p><a class="article-body-image-wrapper" href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fcdn.bsky.app%2Fimg%2Ffeed_fullsize%2Fplain%2Fdid%3Aplc%3Azl7pjaqajbk5mlwalj62hiz2%2Fbafkreifv3e3gf53ep2gi4ofjhjh2cmqi…

相关实体

相关话题