Anthropic 用分类器门控解决了敏感任务的安全分发问题，做 AI 安全或模型部署的团队值得关注这种路由架构的设计思路。
Anthropic 正式推出 Claude Fable 5，这是 Mythos 类模型的公共版本。Fable 5 与 Mythos 5 共享底层模型，但 Fable 增加了分类器门控，用于检测敏感的网络、生物、化学和模型复制请求。当触发门控时，请求不会直接拒绝，而是回退到 Opus 4.8 处理，这是一种模型回退控制机制。该模型支持 100 万 token 上下文窗口，能在 1 天内完成 5000 万行 Ruby 迁移。关键在于，产品已从单一模型转变为路由机器，根据请求内容决定用户可接触的智能层级。Anthropic 表示，回退机制仅在不到 5% 的会话中触发，且限于狭窄主题。
Anthropic finally released Claude Fable 5, a publi…
Anthropic finally released Claude Fable 5, a public Mythos-class model.
Fable 5 and Mythos 5 share one underlying model, but Fable adds classifier gates for everyone while Mythos lifts some gates for vetted cyber and infrastructure partners.
i.e. the public version is wrapped in classifier gates that detect sensitive cyber, biology, chemistry, and model-copying requests.
When those gates trigger, the user does not get a normal refusal; the request is handed to Opus 4.8, which means Anthropic is using model fallback as a control system.
Anthropic says the leap is longer-range autonomy: a 50M-line Ruby migration in 1 day, screenshot-to-code work, has a 1M-token context window,
That is the crucial shift: the product is no longer just a model, but a routing machine that decides which level of intelligence a user is allowed to touch for each request.
The limit is that this routing is not arbitrary and not for every subject; Anthropic says the fallback is triggered by a narrow set of topics and appears in less than 5% of sessions on average.