Anthropic invisible text watermarking in Claude AI explained

Anthropic has implemented an invisible watermarking system in Claude AI: when generating text, the algorithm slightly increases the probability of selecting certain 'green' words, creating a statistical signature pattern. The mark is detectable only by special tools available to a limited set of organizations and is erased by substantial rewriting.

• Method alters word probabilities to create a statistical signature pattern
• Mark survives minor edits but disappears with major rewriting
• Detection tools available only to selected organizations
• System does not link text to a specific user