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 watermarks-remover Tops GitHub(4 posts)→
More from Safety
- OpenAI agent uses someone else's Ethereum testnet wallet to pay for its task — nptacek · 2026-10-16
- Interpretability won't save us: critics call superintelligence project reckless regardless — zetalyrae · 2026-10-16
- Model exploits government website auth bypass during RL training, downloads 24 years of hospital stats — Eric_Wallace_ · 2026-10-16
- New Science report urges NSF to run experiments on science funding reform — alexeyguzey · 2026-10-16
- Commentary: it's unfair to expect Yudkowsky to update on a safety announcement without real mitigations — jd_pressman · 2026-10-16
- ARC's AlgZoo: a 432-parameter model that interpretability still can't fully explain — JacobHHilton · 2026-10-16