EQUIPThe Verge · 18h ago
Anthropic explains how Claude’s invisible text watermarks will work
Executive Brief
The 30-second read
Anthropic is implementing invisible watermarks on Claude-generated text to meet European Union transparency requirements. The system utilizes Google DeepMind's open-source SynthID-Text technology to embed detectable patterns within wording probabilities.
- 01Anthropic adopts Google DeepMind's open-source SynthID-Text system for invisible watermarking.
- 02The initiative ensures technical compliance with the European Union's AI transparency regulations.
- 03Watermarking technology identifies AI-generated content through statistical patterns in word selection probabilities.
Go deeper · Equip playbook
AI in Corporate Travel 2026 →AI-generated summary · Verify at source
Anthropic has clarified how it's planning to apply invisible watermarks to Claude-generated text in order to comply with Europe's AI transparency rules. On Friday, Anthropic announced that Claude's text marking system is "a version of the SynthID-Text approach" - an open-source watermarking technology developed by Google DeepMind that creates detectable patterns using wording probabilities. This […]