The Decoder· Matthias Bastian·· 5 h ago
Anthropic's text watermark is easy to bypass on several older Claude models
Anthropic's text watermark is easy to bypass on several older Claude models
AI summary
Anthropic is rolling out text watermarks to four more Claude models ahead of the EU AI Act's December deadline. But on older models like Claude Opus 4.6 and Sonnet 4.6, API users can disable the watermark by changing a single sampling parameter. Anthropic's response to the loophole? A compliance warning.
Selection record
Threshold 76Media and individualsFirst 52Second 58
Not admittedSum of both 110 < twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：Anthropic文本水印及Claude模型AI功能
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: The Decoder · the-decoder.com