Anthropic Explains How Claude's Invisible Text Watermarks Will Work
1 min read
Image Generation
-/5
In short
- Anthropic has clarified how it plans to apply invisible watermarks to Claude-generated text to comply with Europe's AI transparency regulations.
- 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 create
- This development could have far-reaching implications for regulatory compliance and transparency in the AI sector.
Anthropic has clarified how it plans to apply invisible watermarks to Claude-generated text to comply with Europe's AI transparency regulations. 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 development could have far-reaching implications for regulatory compliance and transparency in the AI sector. It is important to note that the implementation of such technologies presents both opportunities and challenges, particularly concerning privacy protection and the integrity of generated content. A final assessment would be premature at this point.
Source:
-
Anthropic explains how Claude’s invisible text watermarks will work — The Verge (EN-US)