Anthropic 介绍名为 self-assessment 的新技术，让 Claude 在回复后立即对对话做初步安全评估。作者引用数据称，在 Claude Fable 5 上该方法以 1% 误报率标记出强提示词分类器判定有害对话的 78%，高优先级对话达 94%；Anthropic 还称每次成功攻击消耗的生成 token 约为无防护时的四倍。
Anthropic introduced self-assessment, a new technique that lets Claude give each conversation a preliminary safety assessment right after it responds.
On Claude Fable 5, self-assessment flags 78% of the conversations that a stronger, prompted classifier flags as potentially harmful, and 94% of the high-priority ones, at a 1% false-positive rate.
Anthropic also shed light on how self-assessment and prompted classifiers help block attacks.
"Each successful attack costs roughly four times as many generated tokens as with no safeguards."
We already live in a world where your security depends on the compute allocated to defend the systems you rely on.
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：🚨 AI News | TestingCatalog · x.com