Fable に判断を委ね、動作方法を強制しないよう求める
TLDR AI は、AI ツール「Fable」が外部からの細かな指示に縛られるのではなく、自らの判断力(judgement)を行使して行動するべきだと提言した。
キーポイント
自律的判断の推奨
ツールに対して動作方法を外部から指示するのではなく、AI が自身の判断で状況を評価し行動することを強く推奨している。
過度な制御への警鐘
Fable のような AI ツールに対し、人間が詳細な手順を強制することは、本来の能力を発揮させない弊害があると指摘している。
信頼と委譲の重要性
AI に特定のタスクを任せる際は、その判断プロセスへの信頼を持ち、必要以上に介入しない姿勢が重要であると説いている。
影響分析・編集コメントを表示
影響分析
この記事は、AI ツールの設計思想やユーザーとのインタラクションにおいて、「指示と制御」から「自律と判断」へとパラダイムシフトを起こすべきだという重要な示唆を与えています。特に Fable のような特定のツールにおける運用指針として提言されていますが、より広範な AI 活用において、人間が AI に過度に干渉しないことの重要性を再認識させる内容です。
編集コメント
特定のツール名が挙がっていますが、これは AI の自律性を高めるための普遍的な原則を説く良質な提言です。開発者やユーザーは、AI に過度な制御を与えず、その判断力を信じる姿勢の重要性を見直す必要があります。
2026 年 7 月 3 日
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、どのように動作すべきかを指示するのではなく、自らの判断で行動させるようにすることです。
彼らが挙げた例はテストの実施です。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修正についてはテストの更新と実行を行わない」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 自身の判断を使うように指示する方がより良いのです。
Jesse Vincent は、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 トークンを無駄に使いすぎないよう助けるため、私に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し、どのモデルを使うべきかについて自らの判断を適用するように指示することです。
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てそれをサブエージェントとして実行するよう、あなたの判断を用いて決定してください
Claude はこのメモリーファイルを ~/.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
Simon が 2026 年 7 月 3 日に述べています:「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て実行する判断は、サブエージェント(subagent)に任せてください。」
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で保持します。
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ます。設計、監査、データ合成、および判断を要するあらゆる作業は、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、Fable の利用枠が以前よりもゆっくりと減少しています。
原文を表示
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.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