Anthropic 的 Claude 水印功能跳過兩個較舊模型的漏洞
anthropic 為四個更多的 claude 模型添加水印，但 api 用戶可以通過更改採樣參數來繞過兩個較舊模型上的水印。這影響了使用 claude 進行文本生成的公司。
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.