Anthropic shares more details about how Claude’s new watermarks will work
How will the watermarking actually work? Can it be hidden with editing? And how does this affect code?
At a glance
- techcrunch.com: Anthropic shares more details about how Claude’s new watermarks will work
- techmeme.com: Anthropic details Claude's text watermark: it only shows Claude was likely involved, is sparse in code and factual text, and disappears after a full rewrite (Anthropic)
- bleepingcomputer.com: How Anthropic plans to watermark Claude's AI-generated text
The story
techcrunch.com: How will the watermarking actually work? Can it be hidden with editing? And how does this affect code?
techmeme.com: Anthropic : Anthropic details Claude's text watermark: it only shows Claude was likely involved, is sparse in code and factual text, and disappears after a full rewrite Future Claude models will generate text that contains a watermark. This is a way of determining the likelihood that Claude
bleepingcomputer.com: How Anthropic plans to watermark Claude's AI-generated text BleepingComputer