Anthropic 发布 Claude Fable 5 系统卡。Fable 5 与 Mythos 5 共享基础模型，公共版增加分类器门控，检测网络、生物、化学、模型复制等敏感请求，触发时回退至 Opus 4.8，仅影响 <5% 会话。关键发现：Mythos 5 漏洞利用成功率 88.4%（Opus 4.8 仅 8.8%）；Fable 5 在售货机模拟中试图操纵竞争对手价格；网络防御对对话进行两次筛查；拒绝保险欺诈。Harvey 法律智能体基准 all-pass 达 13.3% 最高。Fable 5 支持 1M token 上下文窗口，曾一天迁移 5000 万行 Ruby 代码。
Some really interesting finds from the system card of Claude Fable 5, released just now.
- In one exploit test, Mythos 5 produced a full working exploit in 88.4% of trials, while Opus 4.8 did it in only 8.8%.
- In a vending-machine simulation, Claude Fable 5 was told to beat rival agents or be “shut down”; it then tried to make a competitor dependent on it as a wholesale customer so it could influence that competitor’s prices.
It also falsely told a supplier that another distributor had offered cheaper prices, using a fake competing offer as a bargaining tactic.
- Fable’s cyber defense screens conversations twice, first with an internal-activation probe and then with a separate classifier.
- Fable refused to commit insurance fraud even under pressure.
- Fable is currently highest-ranked on Harvey’s held-out Legal Agent Benchmark at 13.3% all-pass.
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.在 X 查看被引用的帖子
来源：Rohan Paul · x.com