Research finds Claude text watermarking alters meaning
petrusenko_max · x · 2026-08-17
Research reveals that Anthropic's Claude embeds watermarks by subtly skewing word choice probabilities between 'green' and 'red' lists to create detectable fingerprints. Despite claims of imperceptibility, the watermarking is found to actually alter the meaning and quality of the text.
More from Models
- 前沿智能降价如云存储,企业 AI 竞争转向路由与编排层 — krishnan · 2026-08-18
- DeepSeek-V4-Pro Released with Adjustable Reasoning and OpenAI API Compatibility — petrusenko_max · 2026-08-18
- Microsoft Research: 4B model tuned with SocialRL out-negotiates GPT-5 family — dair_ai · 2026-08-17
- Gemini 3.7 Flash Launches with Temporary Low Pricing — KoseteBamse · 2026-08-17
- New Flash model matches Pro in style and performance — teortaxesTex · 2026-08-17
- GLM-5.3 outperforms Fable 5 in 3D web design with 15x lower cost — togethercompute · 2026-08-17