AI 导读
Anthropic 训练 Claude 在每次回答后自行给出对话安全预评估，称其为 self-assessment，自 6 月启用以来发现了其他防护机制未覆盖的滥用行为。
推荐理由
原文给出自我评估机制的核心数据，包括78%至94%的标记匹配率和1%误报率，可了解Claude安全评估的实际效果。
正文
Every time Claude answers, it now quietly asks itself whether it just helped someone cause harm, and that private verdict goes to Anthropic’s reviewers.
Anthropic’s most accurate misuse detector is a Claude Mythos Preview classifier that reads all its safety policies before every ruling, which makes it too expensive to run on every chat.
So Anthropic trained Claude to copy its judgments without the policies or the reasoning, and on Fable 5 traffic the copy matches 78% of the detector’s flags, rising to 94% for high-priority cases, at a 1% false-alarm rate.
We’ve trained Claude to flag potential misuse in conversations, a technique we call self-assessment. Right after it responds, Claude gives a preliminary safety assessment of the conversation. Since we began using self-assessment in June, it has surfaced misuse that our other safeguards weren’t designed to catch. Because Claude has already read the conversation, self-assessment is very efficient. And unlike classifiers, which target a discrete set of harms, it draws on Claude’s own judgment, so it gets more accurate as our models improve. Read more on our new Safeguards blog: https://safeguards.anthropic.com/2026/self-assessment/在 X 查看被引用的帖子
来源：Rohan Paul · x.com