Anthropic shares more details about how Claude’s new watermarks will work

How will the watermarking actually work? Can it be hidden with editing? And how does this affect code?

The top 3

  1. Anthropic's Claude Watermarking Approach: Anthropic is implementing an imperceptible watermark into Claude's text outputs by statistically biasing word choices during generation, making patterns detectable over enough content without affecting quality or readability.
  2. Google's SynthID for Multi-Modal Content: Google DeepMind's SynthID embeds imperceptible digital watermarks directly into AI-generated images, audio, text, and video, designed to withstand modifications like cropping or compression and detectable via a public portal or APIs.
  3. OpenAI's Provenance Signals & C2PA: OpenAI utilizes both SynthID watermarks and the C2PA (Coalition for Content Provenance and Authenticity) open technical standard to embed metadata in images and audio, indicating their origin from OpenAI tools.

Sources

Open the full topic