Anthropic Explains How Claude’s Invisible Text Watermarks Work: The SynthID-Text Mechanism.
To comply with transparency mandates under the European Union’s AI Act (Article 50), AI research lab Anthropic has deployed an invisible text watermarking system across Claude. Rather than embedding hidden Unicode characters, zero-width spaces, or container metadata, Claude uses an adaptation of Google DeepMind’s open-source SynthID-Text architecture. The system introduces statistical patterns into token selection … Read more