Anthropic 发布 FlashProve 原型：加密验证 AI 回复来源且不公开权重
Anthropic's new prototype proves which model wrote an AI response without exposing its weights
精选理由
Anthropic 做了个密码学工具 FlashProve，能验证回复是不是某模型生成的，权重都不用公开，现在是早期原型。
Anthropic 推出研究原型 FlashProve，用密码学方法验证某条 AI 回复是否确实来自声称的模型。验证过程不需要暴露模型权重。Anthropic 说明该系统目前仍有明显局限。这属于模型来源验证方向的一个早期实验。
原文 · Decoder
Anthropic's new prototype proves which model wrote an AI response without exposing its weights
Anthropic has released FlashProve, a research prototype that uses cryptography to verify whether an AI response actually came from the claimed model. The system still has significant limitations. The article Anthropic's new prototype proves which model wrote an AI response without exposing its weights appeared first on The Decoder .
