Anthropic 详解 Claude 隐形文本水印机制
Anthropic explains how Claude’s invisible text watermarks will work
Anthropic has clarified how it's planning to apply invisible watermarks to Claude-generated text in order to comply with Europe's AI transparency rules. On Friday, Anthropic announced that Claude's text marking system is "a version of the SynthID-Text approach" - an open-source watermarking technology developed by Google DeepMind that creates detectable patterns using wording probabilities.
Anthropic已明确其计划如何将隐形水印应用于Claude生成的文本，以符合欧洲的AI透明度规则。周五，Anthropic宣布Claude的文本标记系统是“SynthID-Text方法的一个版本”——这是一种由Google DeepMind开发的开源水印技术，通过使用措辞概率创建可检测的模式。
This watermarking feature, alongside C2PA support for Claude-processed images, is being introduced to meet Anthropic's obligations under the European Union's AI Act, which requires synthetic audio, image, video, and text to include machine-readable marks …
这一水印功能，连同对Claude处理图像的支持C2PA，正在推出以满足Anthropic在欧盟《人工智能法案》下的义务，该法案要求合成音频、图像、视频和文本包含机器可读的标记……
Read the full story at The Verge.
在The Verge阅读完整报道。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力