Anthropic to use Google DeepMind's SynthID-Text to watermark Claude outputs

Anthropic has revealed that its upcoming invisible watermarking system for Claude-generated text will be based on Google DeepMind's open-source SynthID-Text technology. The system works by embedding detectable patterns into text through word probability adjustments. Alongside this, Anthropic is also adding C2PA support for images processed by Claude. Both measures are being introduced to comply with the European Union's AI Act, which mandates machine-readable markings on AI-generated content including text, audio, images, and video.
This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)
Log in to join the discussion and vote.
Log in