Anthropic says text watermarking scheme relies on inconsequential words

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. 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 are fancy autocomplete engines which work by...

Läs hela artikeln hos källan.