We've reset usage limits across our products! For those just starting to test Fable, here's four tips for using it more effectively: 1. Give it bigger, more ambitious tasks than what previous models could handle. 2. Use xhigh/high effort as your default for best performance, med for faster interactive sessions. 3. Rework your skills and CLAUDE.mds. Instructions written for prior models anchor Fable to stale patterns, let it use its own judgment first. 4. Move from providing tasks to providing objectives. Describe what done looks like and how to verify it, then let Fable find the path (/loop and /goal are built for this)
我们已经重置了各个产品的使用限额！对于刚开始测试 Fable 的用户，这里有四条更高效使用它的建议：1. 交给它比以往模型所能处理的任务更大、更有野心的任务。2. 默认使用 xhigh/high effort 以获得最佳表现，在需要更快交互的 session（会话）中使用 med。3. 重新调整你的 skills 和 CLAUDE.mds。为先前模型编写的 instructions（指令）会把 Fable 锚定在过时的模式上，先让它运用自己的判断。4. 从“提供任务”转向“提供目标”。描述“完成”应当是什么样子，以及如何验证，然后让 Fable 自己找到路径（/loop 和 /goal 就是为此构建的）
I've been at Anthropic through every model launch. There's been a few cases I can remember of a launch that stands out and marks a step-change in how we use models: - Claude Opus 3 - Claude Sonnet 3.5 - Claude Opus 4.5 And now Claude Fable 5. With Fable, the model stopped feeling like a tool I direct and started feeling more like something I collaborate with.
我在 Anthropic 经历了每一次模型发布。我能记得的、真正突出的、并标志着我们使用模型方式发生阶段性跃迁的发布只有少数几次：- Claude Opus 3 - Claude Sonnet 3.5 - Claude Opus 4.5 以及现在的 Claude Fable 5。对于 Fable，模型不再像是一个由我来指挥的工具，而开始更像是一个与我协作的对象。