Simon Willison 的博客
2026 年 7 月 3 日
周三在 AIE 上与 Claude Code 团队的 Cat Wu 和 Thariq Shihipar 进行炉边谈话时，我得到的最有趣的建议之一是：让 Fable（以及在一定程度上让 Opus）自行判断，而不是规定它们应该如何工作。
他们举的例子是测试。你可以告诉 Fable“只对较大的功能使用自动化测试，不要为小的文案或设计改动更新和运行测试”——但更好的做法是直接告诉 Fable，在决定是否编写测试时自行判断。
Jesse Vincent 刚刚给了我一个相关建议，帮助我在涨价前仅剩的几天里避免消耗过多宝贵的 Fable 模型 token。告诉 Fable 将较小的任务交给其他模型处理，由它自行判断使用哪个模型。
我刚才用以下提示词向 Claude Code 提问：
对于所有编码任务，请自行判断并选择一个合适的低功耗模型，在子智能体中运行该模型
Claude 将这个记忆文件保存在了 `~/.claude/projects/name-of-project/memory/delegate-coding-to-subagents.md` 中：
--- name: delegate-coding-to-subagents description: Simon wants coding tasks delegated to subagents running an appropriately lower-power model metadata: node_type: memory type: feedback originSessionId: 30068d78-43a9-4fb1-bb29-9799e18c526a ---Simon 于 2026-07-03 声明：“对于所有编码任务，请自行判断并选择一个合适的低功耗模型，在子智能体中运行该模型。”
原因：成本/效率——实现工作通常不需要顶级模型；判断、审查和综合工作仍由主循环负责。
应用方式：当此项目中的任务主要是编写/编辑代码时，生成一个带有模型覆盖（实质性实现用 Sonnet，琐碎/机械性编辑用 Haiku）和自包含提示词的智能体；在提交前于主循环中审查结果。设计、审计、数据综合以及任何需要大量判断的工作仍由主模型处理。另请参见 [[project-goals]]。
到目前为止，效果似乎不错。我完成了大量工作，而我的 Fable 额度消耗速度比以前慢了。
2026 年 7 月 3 日
Simon Willison’s Weblog
3rd July 2026
One of the most interesting tips I got from the Fireside Chat I hosted with Cat Wu and Thariq Shihipar from the Claude Code team at AIE on Wednesday was to let Fable (and to a certain extent Opus) use their own judgement rather than dictating how they should work.
The example they gave was testing. You can tell Fable "only use automated testing for larger features, don't update and run tests for small copy or design changes" - but it's better to just tell Fable to use its own judgement when deciding to write tests instead.
Jesse Vincent just gave me a related tip to help avoid burning too many of those valuable Fable tokens in the few days we have left before the prices go up. Tell Fable to use other models for smaller tasks, applying its own judgement about which model to use.
I prompted Claude Code just now with:
For all coding tasks use your judgement to decide an appropriate lower power model and run that in a subagent
Claude saved this memory file in ~/.claude/projects/name-of-project/memory/delegate-coding-to-subagents.md:
--- name: delegate-coding-to-subagents description: Simon wants coding tasks delegated to subagents running an appropriately lower-power model metadata: node_type: memory type: feedback originSessionId: 30068d78-43a9-4fb1-bb29-9799e18c526a ---Stated by Simon on 2026-07-03: "For all coding tasks use your judgement to decide an appropriate lower power model and run that in a subagent."
Why: cost/efficiency — implementation work rarely needs the top-tier model; judgment, review, and synthesis stay with the main loop.
How to apply: when a task in this project is primarily writing/editing code, spawn an Agent with a model override (sonnet for substantive implementation, haiku for trivial/mechanical edits) and a self-contained prompt; review the result in the main loop before committing. Design, auditing, data synthesis, and anything judgment-heavy stays in the main model. See also [[project-goals]].
So far it seems to be working well. I'm getting a ton of work done and my Fable allowance is shrinking less quickly than before.
3rd July 2026