Anthropic · DeepSeek · Nvidia · Claude · Google · Russia · The Register
Anthropic confirms text watermarking scheme relies on inconsequential words
Compiled by KHAO Editorial — aggregated from 1 source + 1 reference discovered via search. See llms.txt for citation guidance.
◌ Single Source
'Shall the reporter compare thee to a summer's afternoon' is the sort of thing this will make, and others look likely to adopt it.
Key facts
- That's the theory, but when asked to complete that sentence, Claude Opus 4.8 went a bit overboard: "…crisp, the kind of cold that nips at your fingertips and turns your breath to little clouds
- In an effort to "watermark" text that Claude has generated and comply with the EU AI Act, Anthropic ib Friday unveiled a plan on Friday to modify its bots' choice of words in a way
- Shall the reporter compare thee to a summer's afternoon' is the sort of thing this will make, and others look likely to adopt it
- Traditional watermarks are patterns or images overlaid on currency, postage, or official documents as an assertion of authenticity
Summary
In an effort to "watermark" text that Claude has generated and comply with the EU AI Act, Anthropic ib Friday unveiled a plan on Friday to modify its bots' choice of words in a way that would be detectable as the product of an AI. Traditional watermarks are patterns or images overlaid on currency, postage, or official documents as an assertion of authenticity. 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 are fancy autocomplete engines which work by predicting the next word in a sequence of words.