{
  "id": 924735,
  "title": "Anthropic says text watermarking scheme relies on inconsequential words",
  "url": "https://urgent.news/2026/08/15/anthropic-says-text-watermarking-scheme-relies-on-inconsequential",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-15T00:44:41.000Z",
  "source": {
    "name": "The Register",
    "slug": "the-register",
    "url": "https://www.theregister.com/ai-and-ml/2026/08/15/anthropic-says-text-watermarking-scheme-relies-on-inconsequential-words/5288156"
  },
  "original_language": "en",
  "account": "Anthropic has introduced a text watermarking scheme designed to watermark AI-generated text in compliance with the EU AI Act. This watermark will subtly alter the choice of words in Claude's responses, making them detectable as AI-generated. Traditional watermarks, like those on banknotes or official documents, are more rigid patterns or images. In contrast, digital watermarks can take many forms, and Anthropic's approach involves influencing the word choices made by its large language models.\n\nLarge language models, such as Claude, predict the next word in a sequence of words. For instance, when asked to complete the sentence \"The weather today was cold and...\", Claude might typically respond with \"cold\" or \"gray,\" but less likely with \"sugary.\" However, when Claude is forced to complete the sentence in a different way, it demonstrates the technique behind Anthropic's watermarking. By removing the training that encourages engaging and literary-style responses, Claude essentially predicts the next word in a sequence, introducing subtle, context-specific modifications into the generated text.\n\nAnthropic asserts that this watermarking process will not significantly impact the content, creativity, or readability of Claude's text. In internal testing, they found no difference in quality between watermarked and unwatermarked answers when measured by human raters. However, Anthropic emphasizes that this watermarking technique is intended to be applied only to inconsequential text, such as less critical or factual passages, and not to code or high-stakes literature. They state that in most cases, the example sentences could be completed using interchangeable words without altering the overall meaning.\n\nWhile Anthropic's watermarking scheme is not overly intrusive and does not involve any personally identifying information, it is expected to be only semi-effective. In their FAQs, they note that some editing should be sufficient to remove the watermark, while a complete rewrite of the text would eliminate the watermarked distinction. Anthropic views this watermarking as a matter of legal compliance, with minimal impact on the speed of their models and no additional cost for serving and using the model.",
  "summary": "And other AI model makers are expected to deploy something similar",
  "key_points": [
    "Anthropic introduces text watermarking scheme for Claude AI.",
    "Watermark subtly alters word choices in AI-generated text.",
    "Scheme focuses on inconsequential text, not code or critical literature."
  ],
  "editors_take": "Anthropic's text watermarking scheme, designed for EU AI Act compliance, subtly alters word choices in AI-generated text, with minimal impact on content, but is only semi-effective and limited to inconsequential passages.",
  "illustration": null,
  "coverage": {
    "outlets": 2,
    "also_reported_by": [
      {
        "outlet": "The Register Science",
        "title": "Anthropic says text watermarking scheme relies on inconsequential words",
        "url": "https://urgent.news/2026/08/15/anthropic-says-text-watermarking-scheme-relies-on-inconsequential-926149",
        "published": "2026-08-15T00:44:41.000Z"
      }
    ]
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}