Fable の判断力を活用する重要性について
Simon Willison は、AI エージェントに厳格なルールを課すのではなく、タスクの規模に応じて自律的にモデルを選択・実行させる「判断力」の委譲が、コスト効率と生産性を劇的に向上させる実証例を示した。
キーポイント
自律的な判断力の委譲
AI エージェントに対して「小規模な変更にはテストを生成しない」といった細かなルールを指示するのではなく、エージェント自身に状況に応じて判断させるアプローチが推奨される。
コスト最適化のためのモデル選択
実装作業など単純なタスクには低電力モデル(例:Haiku)をサブエージェントとして使い、複雑な設計やレビューはメインの高性能モデル(例:Sonnet/Fable)が担当する階層型ワークフローを構築した。
メモリ機能による継続的学習
Claude Code は、この戦略をプロジェクトごとのメモリファイルとして保存し、セッションを超えて一貫して適用することで、トークン消費の抑制と作業効率の向上を実現している。
重要な引用
"it's better to just tell Fable to use its own judgement when deciding to write tests instead."
"For all coding tasks use your judgement to decide an appropriate lower power model and run that in a subagent"
"implementation work rarely needs the top-tier model; judgment, review, and synthesis stay with the main loop."
影響分析・編集コメントを表示
影響分析
この記事は、LLM コスト管理とエージェント設計におけるパラダイムシフトを示唆しています。従来の「人間がすべてのロジックを定義する」アプローチから、「AI に判断権限を与え、コスト対効果の高いリソース配分を自律的に実行させる」アプローチへの転換を促しており、実務レベルでの AI エージェント運用効率化の重要な指針となります。
編集コメント
「AI に判断を委ねる」という一見抽象的な指示が、具体的なコスト削減と生産性向上に直結する実例として非常に示唆に富んでいます。開発者が AI エージェントを運用する際、ルールベースの硬直的な制御から、能力に応じた動的リソース割り当てへの転換が今後の標準となるでしょう。
水曜日に AIE で Cat Wu と Thariq Shihipar(Claude Code チーム所属)と共催した Fireside Chat から得た、最も興味深いヒントの一つは、Fable(およびある程度 Opus)に自らの判断力(judgement)を使わせ、どのように作業すべきかを指示するのではなく、その判断を委ねることでした。
彼らが挙げた例はテストです。Fable に「大規模な機能には自動化されたテストのみを使用し、小さなコピーやデザインの変更については更新してテストを実行しないように」と伝えることもできますが、テストを書くかどうかを決定する際に Fable 自身の判断を使わせるよう指示する方がより良いのです。
Jesse Vincent が、価格引き上げまで残り数日という限られた期間内で貴重な Fable トークンをあまり使い果たさないための関連するヒントを教えてくれました。Fable に小さなタスクには他のモデルを使用させ、どのモデルを使うべきかについて自らの判断を適用させるよう指示することです。
直近で Claude Code に対して以下のようにプロンプトしました:
**
すべてのコーディングタスクにおいて、適切な低電力モデルを選択し、それをサブエージェント(subagent)として実行するよう自らの判断力を使って決定してください
Claude はこのメモファイルを ~/.claude/projects/name-of-project/memory/delegate-coding-to-subagents.md として保存しました:
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
2026 年 7 月 3 日に Simon が述べています:「すべてのコーディングタスクについては、あなたの判断力を用いて適切な低電力モデルを選択し、それをサブエージェントで実行してください。」
理由: コストと効率性 — 実装作業には最高峰のモデルを必要とするケースは稀であり、判断、レビュー、統合はメインループに残すべきです。
適用方法: このプロジェクト内のタスクが主にコードの記述や編集である場合、モデルオーバーライド(本格的な実装には Sonnet、些細な機械的な編集には Haiku)と自己完結型のプロンプトを指定してエージェントを起動し、コミットする前にメインループで結果を確認してください。設計、監査、データ合成、および判断力が求められるあらゆる作業は、メインモデルで行います。また [[project-goals]] も参照してください。
これまでにうまく機能しているようです。非常に多くの作業をこなせており、私の Fable の利用枠が以前よりもゆっくりと減少しています。
Tags: claude, ai, claude-code, llms, prompt-engineering, coding-agents, generative-ai, claude-mythos-fable, anthropic
原文を表示
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.
Tags: [claude](https://simonwillison.net/tags/claude), [ai](https://simonwillison.net/tags/ai), [claude-code](https://simonwillison.net/tags/claude-code), [llms](https://simonwillison.net/tags/llms), [prompt-engineering](https://simonwillison.net/tags/prompt-engineering), [coding-agents](https://simonwillison.net/tags/coding-agents), [generative-ai](https://simonwillison.net/tags/generative-ai), [claude-mythos-fable](https://simonwillison.net/tags/claude-mythos-fable), [anthropic](https://simonwillison.net/tags/anthropic)関連記事
今日のまとめ
AI日報で今日の重要ニュースをまとめ読み