Anthropic's Claude watermark skips two older models with a tweak
anthropic adds watermark to four more claude models but api users can bypass it on two older models by changing a sampling parameter. this affects companies using claude for text generation.
anthropic is adding a watermark to four more claude models: mythos 5, opus 4.7, opus 4.6, and sonnet 4.6. the watermark is an imperceptible pattern in word choice that doesn't change meaning, quality, or readability. on opus 4.6 and sonnet 4.6, the watermark only applies when developers use default sampling settings. changing these settings can bypass the watermark. anthropic points to the eu ai act's december deadline as the reason for watermarking older models. the company uses a variant of google deepmind's synthid text method.