Claude Watermark Removal Tool Goes Viral After Anthropic Announcement
量子位 · wechat · 2026-08-15
Following Anthropic's announcement of watermarks for Claude, developer Guillaume Meyer released the open-source tool 'watermarks-remover', which quickly garnered 2.6k stars on GitHub. The tool effectively removes metadata-based watermarks like hidden Unicode characters and C2PA signatures. For statistical token-level watermarks (speculated to be KGW), it attempts to disrupt patterns by rewriting or back-translating text via another model. The article also notes that OpenAI and Google previously withheld similar tech due to user resistance.
Related event: Open-Source Tool Strips Invisible AI Watermarks After Claude Rollout(3 posts)→
More from Safety
- tl;dv data isolation flaw exposes 180k meeting records — emmanuelvivier · 2026-08-15
- Google allows disabling visible AI watermarks while keeping invisible SynthID and C2PA — emmanuelvivier · 2026-08-15
- EU AI Act transparency rules take effect: chatbots and deepfakes require clear labels — emmanuelvivier · 2026-08-15
- Researchers exploit Zoom zero-click vulnerability using fewer than 20 AI prompts — emmanuelvivier · 2026-08-15
- US to Demand Allies Choose Sides in AI Race, Sparking 'Polycentric Synth Feudalism' Debate — tedmitew · 2026-08-15
- Plaintiff sanctioned for hiding invisible AI prompts in court filings — The Decoder · 2026-08-15