{
  "id": 9120524,
  "title": "How AI Watermarking Actually Works at the Token Level — And Why Developers Should Pay Attention",
  "url": "https://urgent.news/2026/09/22/how-ai-watermarking-actually-works-at-the-token-level-and-why",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-22T04:31:36.000Z",
  "source": {
    "name": "HackerNoon",
    "slug": "hackernoon",
    "url": "https://hackernoon.com/how-ai-watermarking-actually-works-at-the-token-level-and-why-developers-should-pay-attention?source=rss"
  },
  "original_language": "en",
  "account": "On August 11, 2026, Anthropic announced that Claude would begin embedding watermarks into the text it generates. This change came nine days after the EU AI Act, Article 50, took effect on August 2. Unlike traditional watermarks, the AI watermark operates at the token level, meaning it's embedded within the model during word selection, making it invisible to readers and undetectable without a specific cryptographic key.",
  "summary": "Anthropic is watermarking Claude's output at the token level. Here's how the green/red list mechanism works and what it means for developers building on LLM API",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "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."
}