Anthropic says text watermarking scheme relies on inconsequential words
ai and ml
Ai,Ensures,Compliance,With,Automated,Policy,Checks,,Smart,Regulation,Systems,Copyright (c) 2026 Summit Art Creations/Shutterstock. No use without permission.https://www.shutterstock.com/image-photo/ai-ensures-compliance-automated-policy-checks-2760888993?trackingId=9cad4179-21b0-4a1d-a4ee-4cfe9b1cef45&listId=searchResults
And other AI model makers are expected to deploy something similar
In an effort to "watermark" text that Claude has generated and comply with the EU AI Act, Anthropic unveiled a plan on Friday to modify its bots' choice of words in a way that would be detectable as AI.
Traditional watermarks are patterns or images overlaid on currency, postage, or official documents as an assertion of authenticity. In the digital realm, the term is more flexible and can refer to a variety of techniques for applying an identifier to electronic data.
Anthropic's approach involves influencing inconsequential word choices made by its models, a technique introduced in Google DeepMind's SynthID-Text paper.
To oversimply things, large language models work by predicting the next word in a sequence of words. The AI biz explainsthat while composing...
Copyright of this story solely belongs to theregister.com. To see the full text click HERE
