Commit graph

6 commits

Author SHA1 Message Date
Florian BRUNIAUX
8fe99ca515 docs: add Matteo Collina practitioner insight (bottleneck shift thesis)
Add Node.js TSC Chair's perspective on human judgment in AI-assisted development:
- Full entry in ai-ecosystem.md Practitioner Insights section
- Reference in learning-with-ai.md Practitioner Perspectives
- YAML index entries in reference.yaml

Key concepts integrated:
- Bottleneck shift from coding to reviewing
- "The human in the loop isn't a limitation. It's the point."
- Cultural warning against "AI wrote it" as excuse
- Data: Review time +91%, 96% developers don't trust AI code

Context: Response to Arnaldi's "Death of Software Development" (Jan 2026)

Co-Authored-By: Claude <noreply@anthropic.com>
2026-01-23 11:26:50 +01:00
Florian BRUNIAUX
377f5dbce1 docs: add OCTO Technology reference to learning-with-ai.md
Added organizational perspective on AI-augmented development to
Practitioner Perspectives section. Key insights: pairs as minimal
team unit (bus factor), bottleneck shifts to functional requirements.

Co-Authored-By: Claude <noreply@anthropic.com>
2026-01-23 10:00:35 +01:00
Florian BRUNIAUX
09eb141976 docs: v3.9.6 - Trust Calibration, Vibe Coding Trap, reference.yaml sync
Added:
- ultimate-guide.md: Trust Calibration section (1.7) with research-backed verification strategies
- ultimate-guide.md: Infrastructure as Code Skills (Anton Babenko's terraform-skill)
- learning-with-ai.md: "The Vibe Coding Trap" anti-pattern (Karpathy, Feb 2025)
- learning-with-ai.md: "Reality of AI Productivity" section with research
- learning-with-ai.md: External resource link to leerob.com/ai (AI fundamentals)
- IDEAS.md: "Vibe Coding Discourse" watching entry

Changed:
- reference.yaml: Complete line number synchronization (~55 entries)
  Guide grew from ~9900 to 11154 lines; all deep_dive references updated
- Version bump: 3.9.5 → 3.9.6

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-20 08:36:35 +01:00
Florian BRUNIAUX
fd17414abb docs: add AI productivity research, trust calibration, and exploration workflow
## New Content

### Trust & Verification (ultimate-guide.md)
- Section 1.7 "Trust Calibration: When and How Much to Verify" (~155 lines)
  - Research-backed stats (ACM, Veracode, CodeRabbit, Cortex.io)
  - Verification spectrum by code type
  - Solo vs Team strategies with workflow diagrams
  - "Prove It Works" checklist
- New pitfall: "Trust AI output without proportional verification"
- CLAUDE.md size guideline: 4-8KB optimal, >16K degrades coherence

### AI Productivity (learning-with-ai.md)
- Section "The Reality of AI Productivity" (~55 lines)
  - Productivity curve phases (Wow Effect → Targeted Gains → Plateau)
  - High-gain vs low/negative-gain task categorization
  - Team success factors
- Productivity trajectory table by pattern (Dependent/Avoidant/Augmented)
- 5 new sources (GitHub, McKinsey, Stack Overflow, Uplevel, DORA)

### Session Limits (architecture.md)
- "Session Degradation Limits" section
  - Turn limits (15-25), token thresholds (80-100K)
  - Success rates by scope (1-3 files: ~85%, 8+ files: ~40%)

### Exploration Workflow
- NEW: guide/workflows/exploration-workflow.md
  - Anti-anchoring prompts, 3-5 approaches pattern
- iterative-refinement.md: Script Generation Workflow (3-7 iteration pattern)
- anchor-catalog.md: Anti-Anchoring Techniques, Exploration/Iteration Prompts

### Reference Updates
- adoption-approaches.md: Empirical data section
- reference.yaml: New deep_dive entries, updated line numbers

Sources: MetalBear engineering blog, arXiv studies, Addy Osmani (Jan 2026)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-19 19:16:33 +01:00
Florian BRUNIAUX
dab11d260c feat: reorganize learning commands under /learn namespace
- Move quiz.md → learn/quiz.md (/learn:quiz)
- Add learn/teach.md (/learn:teach) for step-by-step concept explanations
- Add learn/alternatives.md (/learn:alternatives) for approach comparisons
- Update all references in guide, README, and reference.yaml

Follows Claude Code namespaced commands convention:
/namespace:command → .claude/commands/namespace/command.md

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-19 11:13:54 +01:00
Florian BRUNIAUX
7fd4048d5e feat: add learning guide & website badge
- Add "Visit Website" badge to README.md (prominent, top position)
- Add learning-with-ai.md guide for junior developers (~900 lines)
  - UVAL Protocol, dependency patterns, 30-day progression plan
- Add 3 learning templates (55 total):
  - examples/claude-md/learning-mode.md
  - examples/commands/quiz.md
  - examples/hooks/bash/learning-capture.sh
- Fix template count: 52 → 55 (was incorrectly showing 56)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-17 18:42:34 +01:00