torben
a35c94e2d9
Files changed: - kb/concepts/Ambient Environment Dependency.md - kb/concepts/Anti-Cramming Heuristic.md - kb/concepts/Audit Trail.md - kb/concepts/BM25.md - kb/concepts/Bulk Operations.md - kb/concepts/CI Integration.md - kb/concepts/CPPC.md - kb/concepts/Checkpoint Audit.md - kb/concepts/Claude Code Auto Mode.md - kb/concepts/Command Round-Trip Integrity.md - kb/concepts/Confidence Scoring.md - kb/concepts/Consolidation Tiers.md - kb/concepts/Content Quality Control.md - kb/concepts/Context Isolation.md - kb/concepts/Contradiction Resolution.md - kb/concepts/Cross-platform Agent Skills.md - kb/concepts/Crystallization.md - kb/concepts/Delete Rather Than Anonymize.md - kb/concepts/Denylist over Allowlist.md - kb/concepts/Detect-Repair Asymmetry.md - kb/concepts/Diff-Reviewable Agent Edits.md - kb/concepts/Dual Licensing by File Plan.md - kb/concepts/Entity Extraction.md - kb/concepts/Episodic Memory.md - kb/concepts/Event-Driven Automation.md - kb/concepts/Filter on Ingest.md - kb/concepts/Forgetting.md - kb/concepts/Graph Traversal.md - kb/concepts/Green Suite Blind Spot.md - kb/concepts/Hooks.md - kb/concepts/Hybrid Search.md - kb/concepts/Implementation Spectrum.md - kb/concepts/Index Scaling.md - kb/concepts/Issue Label Scheme.md - kb/concepts/Iteration and Cost Limits.md - kb/concepts/KB Migration.md - kb/concepts/KB Stack Versioning.md - kb/concepts/Knowledge Compounding.md - kb/concepts/Knowledge Graph.md - kb/concepts/LLM Wiki Pattern.md - kb/concepts/Lint Workflow.md - kb/concepts/MCP-Leseserver.md - kb/concepts/Mass-Update Gate.md - kb/concepts/Memory Lifecycle.md - kb/concepts/Mesh Sync.md - kb/concepts/Modbus.md - kb/concepts/Multi-Agent Collaboration.md - kb/concepts/Naming Convention Conflict.md - kb/concepts/OKF Compatibility.md - kb/concepts/Optional Instance Context File.md - kb/concepts/Personalization Plane.md - kb/concepts/Privacy and Governance.md - kb/concepts/Procedural Memory.md - kb/concepts/Publish-Remote Gate.md - kb/concepts/Quality Scoring.md - kb/concepts/Quality and Self-Correction.md - kb/concepts/RAG.md - kb/concepts/Reciprocal Rank Fusion.md - kb/concepts/SSD TRIM.md - kb/concepts/Scale Ceiling.md - kb/concepts/Self-Healing.md - kb/concepts/Semantic Lint Automation.md - kb/concepts/Semantic Memory.md - kb/concepts/Session Orientation.md - kb/concepts/Shared vs Private.md - kb/concepts/Split Merge Reclassify.md - kb/concepts/Split Threshold.md - kb/concepts/Structural Enforcement over Documented Rule.md - kb/concepts/Stub Threshold.md - kb/concepts/Supersession.md - kb/concepts/Three-Layer Architecture.md - kb/concepts/Token Economics.md - kb/concepts/Typed Relationships.md - kb/concepts/User Management.md - kb/concepts/Vector Search.md - kb/concepts/Work Coordination.md - kb/concepts/Workflow Extraction.md - kb/concepts/Workflow Orchestration.md - kb/concepts/Working Memory.md - kb/concepts/Write-Once Frontmatter Fields.md - kb/log.md - work/link-taxonomy-migration/glossary.md
63 lines
2.5 KiB
Markdown
63 lines
2.5 KiB
Markdown
---
|
|
type: types/concept.md
|
|
concept_type: architecture
|
|
tags: [scale, limitations]
|
|
created: 2026-08-04
|
|
modified: 2026-09-01
|
|
related:
|
|
- see-also: Token Economics
|
|
- see-also: Cross-platform Agent Skills
|
|
- see-also: Context Isolation
|
|
sources: [Source - Copilot Skill Restructure Instructions]
|
|
confidence: 0.80
|
|
confidence_base: 0.80
|
|
provenance: sourced
|
|
summary: Punkt, ab dem Wiki-Ansätze mit einem einzigen Kontext qualitativ abfallen
|
|
---
|
|
# Scale Ceiling
|
|
|
|
**Typ:** architecture
|
|
|
|
## Definition
|
|
|
|
Scale Ceiling ist der Punkt, an dem Single-Context-Wiki-Ansätze (eine große Anweisungsdatei, vollständiger Index wird jede Sitzung neu gelesen) an Qualität degradieren, typischerweise sobald ein Wiki etwa 100-200 Seiten überschreitet[^s-copilot-skill-restructure-instructions].
|
|
|
|
## Kernpunkte
|
|
|
|
- **Qualitätsverschlechterung**: Mit wachsendem Wiki verlieren LLMs Verbindungen und die Qualität sinkt mit Single-Context-Ansätzen[^s-copilot-skill-restructure-instructions]
|
|
- **Schwellenwert**: Evidenz deutet darauf hin, dass die Verschlechterung um die 100-200 Seiten beginnt[^s-copilot-skill-restructure-instructions]
|
|
- **Symptom**: Das LLM verliert Verbindungen zwischen verwandten Informationen
|
|
- **Lösung**: Zu kontextisoliert, Skill-basierten Ansätzen übergehen
|
|
|
|
## Beispiele
|
|
|
|
- Dokumentierter Fall: RTFM/Retrieval-Layer-Ansatz bei einem 8.260-Datei-Corpus erreichte 100% Erfolgsquote (von ~55-64%) durch Bereitstellung von Metadaten zuerst und Erweiterung nur das Notwendige[^s-copilot-skill-restructure-instructions]
|
|
- Das Chemenu-Repository nähert sich dem Scale Ceiling mit monolithischer AGENTS.md[^s-copilot-skill-restructure-instructions]
|
|
|
|
## Wann zu verwenden
|
|
|
|
Scale Ceiling beachten, wenn:
|
|
- Das Wiki sich 100 Seiten nähert oder überschreitet
|
|
- Das LLM Verbindungen zwischen verwandtem Inhalt vermisst
|
|
- Die Abfragequalität inkonsistent oder verschlechtert ist
|
|
- Für langfristiges Wiki-Wachstum geplant wird
|
|
|
|
## Wann NICHT zu verwenden
|
|
|
|
Scale Ceiling ist kein Problem wenn:
|
|
- Das Wiki klein ist und klein bleiben soll
|
|
- Retrieval-Augmented-Ansätze genutzt werden, die alles in den Kontext laden vermeiden
|
|
- Die Workflows kein Verständnis von Verbindungen über das gesamte Wiki erfordern
|
|
|
|
## Fußnoten
|
|
|
|
[^s-copilot-skill-restructure-instructions]: [[Source - Copilot Skill Restructure Instructions]]
|
|
|
|
<!-- wikitool:links -->
|
|
## Beziehungen
|
|
|
|
- **see-also:** [[Token Economics]]
|
|
- **see-also:** [[Cross-platform Agent Skills]]
|
|
- **see-also:** [[Context Isolation]]
|
|
<!-- /wikitool:links -->
|