---
id: 20260704-T0-16
title: "Claude Code团队建议：让Fable独立判断，别强行规定工作方式"
title_en: "Claude Code Team: Let Fable Use Its Own Judgment for Better Testing"
url: https://ai.daily.yangsir.net/daily/20260704-T0-16
issue_date: 2026-07-04
publish_date: 2026-07-03T18:51:06.000Z
source_name: "Simon Willison"
source_url: https://simonwillison.net/2026/Jul/3/judgement/#atom-everything
---

# Claude Code团队建议：让Fable独立判断，别强行规定工作方式

在AIE Fireside Chat上，Claude Code团队的Cat Wu和Thariq Shihipar分享了一个关键技巧：在测试等任务中，让模型Fable(及Opus)使用自己的判断力，而不是强制规定它们的工作方式。这一方式能显著提升测试效果和效率。

## English Version

**Claude Code Team: Let Fable Use Its Own Judgment for Better Testing**

At AIE Fireside Chat, Claude Code team members Cat Wu and Thariq Shihipar shared a critical tip: in testing and other tasks, let models like Fable (and Opus) use their own judgment instead of dictating how they should work. This approach significantly improves testing quality and efficiency.

---

**来源**：[Simon Willison](https://simonwillison.net/2026/Jul/3/judgement/#atom-everything)

**详情页**：https://ai.daily.yangsir.net/daily/20260704-T0-16

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*