行业动态
x.com ·
@OpenAI
OpenAI 解释文本水印机制：嵌入不可见统计信号，不影响模型能力与速度
OpenAI 官方说明文本水印用于回答“这段文本是否可能由 OpenAI 模型生成”，通过在生成时嵌入不可见统计信号实现，检测器可识别该信号，不添加可见标记或特殊字符。水印不表明原作者或所有权，也不识别个人、组织、账号、对话或提示。OpenAI 称测试中水印未影响模型能力、速度或回答可读性。
AI推荐理由 OpenAI 官方解释文本水印机制：在生成时嵌入不可见统计信号，检测器据此判断文本是否可能由 OpenAI 模型生成，不添加可见标记，不识别作者、组织或提示。并称测试中水印未影响模型能力、速度或可读性。属官方技术说明，事实明确。
70
浏览 396,054
点赞 827
评论 56
转发 42
正文
When possible, we want to give people a choice—and be clear about what watermarking can and can’t do.
A text watermark helps answer one question: “Was this likely generated by an OpenAI model?”
It works by embedding an invisible statistical signal in text as it’s generated. A detector can look for this signal, and it doesn’t add visible marks or special characters. It doesn’t say who originally wrote the text or who owns it. It doesn’t identify a person, organization, account, conversation, or prompt.
In our testing, watermarking hasn’t affected how capable or fast our models are, or how their responses read.