docs: clarify model-generation reference in learn-eval rationale

The design rationale cited "Opus 4.6+" as the class of models capable of
holistic checklist judgment. That reference predates the Claude 5 families
(Opus 5, Sonnet 5, Fable 5), so readers on current models can't tell whether
the guidance still applies to them.

Widens the parenthetical to name the Claude 5 families explicitly. Applied
across all four locale copies (en, ja-JP, tr, zh-CN) to keep translations in
sync. Documentation wording only; no behavioral change.
This commit is contained in:
Phumchai Tanonsi
2026-08-24 22:26:32 -03:00
committed by Alex Schmitt
parent d8409a4b08
commit 774d64f51b
4 changed files with 4 additions and 4 deletions
+1 -1
View File
@@ -142,7 +142,7 @@ directory name and frontmatter `name:` identical.
## Design Rationale
This version replaces the previous 5-dimension numeric scoring rubric (Specificity, Actionability, Scope Fit, Non-redundancy, Coverage scored 1-5) with a checklist-based holistic verdict system. Modern frontier models (Opus 4.6+) have strong contextual judgment — forcing rich qualitative signals into numeric scores loses nuance and can produce misleading totals. The holistic approach lets the model weigh all factors naturally, producing more accurate save/drop decisions while the explicit checklist ensures no critical check is skipped.
This version replaces the previous 5-dimension numeric scoring rubric (Specificity, Actionability, Scope Fit, Non-redundancy, Coverage scored 1-5) with a checklist-based holistic verdict system. Modern frontier models (Opus 4.6+, including the Claude 5 families) have strong contextual judgment — forcing rich qualitative signals into numeric scores loses nuance and can produce misleading totals. The holistic approach lets the model weigh all factors naturally, producing more accurate save/drop decisions while the explicit checklist ensures no critical check is skipped.
## Notes
+1 -1
View File
@@ -105,7 +105,7 @@ origin: auto-extracted
## 設計の根拠
このバージョンは、以前の5ディメンション数値スコアリングルーブリック(Specificity、Actionability、Scope Fit、Non-redundancy、Coverageを1-5でスコアリング)をチェックリストベースの総合判定システムに置き換えています。最新のフロンティアモデル(Opus 4.6+)は強力なコンテキスト判断能力を持っており、豊かな定性的シグナルを数値スコアに強制すると、ニュアンスが失われ、誤解を招く合計を生み出す可能性があります。総合的なアプローチにより、モデルがすべての要因を自然に重み付けし、明示的なチェックリストが重要なチェックのスキップを防ぎながら、より正確な保存/破棄の決定を生み出します。
このバージョンは、以前の5ディメンション数値スコアリングルーブリック(Specificity、Actionability、Scope Fit、Non-redundancy、Coverageを1-5でスコアリング)をチェックリストベースの総合判定システムに置き換えています。最新のフロンティアモデル(Opus 4.6+、Claude 5 系列を含む)は強力なコンテキスト判断能力を持っており、豊かな定性的シグナルを数値スコアに強制すると、ニュアンスが失われ、誤解を招く合計を生み出す可能性があります。総合的なアプローチにより、モデルがすべての要因を自然に重み付けし、明示的なチェックリストが重要なチェックのスキップを防ぎながら、より正確な保存/破棄の決定を生み出します。
## 注意事項
+1 -1
View File
@@ -105,7 +105,7 @@ origin: auto-extracted
## Tasarım Gerekçesi
Bu versiyon, önceki 5 boyutlu sayısal puanlama rubriğini (Spesifiklik, Uygulanabilirlik, Kapsam Uyumu, Gereksizlik Olmama, Kapsama 1-5 arası puanlanıyor) kontrol listesi tabanlı bütünsel karar sistemiyle değiştirir. Modern frontier modeller (Opus 4.6+) güçlü bağlamsal yargıya sahiptir — zengin niteliksel sinyalleri sayısal skorlara zorlamak nüans kaybettirir ve yanıltıcı toplamlar üretebilir. Bütünsel yaklaşım, modelin tüm faktörleri doğal olarak tartmasına izin vererek daha doğru kaydet/düşür kararları üretirken, açık kontrol listesi kritik hiçbir kontrolün atlanmamasını sağlar.
Bu versiyon, önceki 5 boyutlu sayısal puanlama rubriğini (Spesifiklik, Uygulanabilirlik, Kapsam Uyumu, Gereksizlik Olmama, Kapsama 1-5 arası puanlanıyor) kontrol listesi tabanlı bütünsel karar sistemiyle değiştirir. Modern frontier modeller (Opus 4.6+, Claude 5 aileleri dahil) güçlü bağlamsal yargıya sahiptir — zengin niteliksel sinyalleri sayısal skorlara zorlamak nüans kaybettirir ve yanıltıcı toplamlar üretebilir. Bütünsel yaklaşım, modelin tüm faktörleri doğal olarak tartmasına izin vererek daha doğru kaydet/düşür kararları üretirken, açık kontrol listesi kritik hiçbir kontrolün atlanmamasını sağlar.
## Notlar
+1 -1
View File
@@ -106,7 +106,7 @@ origin: auto-extracted
## 设计原理
此版本用基于清单的整体裁决系统取代了之前的 5 维度数字评分标准(具体性、可操作性、范围契合度、非冗余性、覆盖度,评分 1-5)。现代前沿模型(Opus 4.6+)具有强大的情境判断能力 —— 将丰富的定性信号强行压缩为数字评分会丢失细微差别,并可能产生误导性的总分。整体方法让模型自然地权衡所有因素,产生更准确的保存/放弃决策,同时明确的清单确保不会跳过任何关键检查。
此版本用基于清单的整体裁决系统取代了之前的 5 维度数字评分标准(具体性、可操作性、范围契合度、非冗余性、覆盖度,评分 1-5)。现代前沿模型(Opus 4.6+,包括 Claude 5 系列)具有强大的情境判断能力 —— 将丰富的定性信号强行压缩为数字评分会丢失细微差别,并可能产生误导性的总分。整体方法让模型自然地权衡所有因素,产生更准确的保存/放弃决策,同时明确的清单确保不会跳过任何关键检查。
## 注意事项