vault: add ECC methodology deep-dive and zettelkasten insights

New resource note with 6 core methodologies, community best practices,
pitfalls, and practical examples. Three zettelkasten notes extract key
insights: hook vs prompt reliability, MCP context tradeoffs, and the
instinct learning system. Updated existing guides with cross-links.
This commit is contained in:
Yaojia Wang
2026-03-19 23:19:56 +01:00
parent e4382d01bb
commit 872401be72
6 changed files with 430 additions and 32 deletions

View File

@@ -0,0 +1,30 @@
---
created: "2026-03-19 12:03"
type: zettel
tags: [claude-code, machine-learning, continuous-improvement, agent-evolution]
source: "https://github.com/affaan-m/everything-claude-code"
---
# 本能学习系统的演化路径
ECC 的 Continuous Learning v2.1 实现了一个 AI Agent 自我改进的闭环:
```
观察(Hook捕获) → 模式检测(Haiku模型) → 本能(Instinct) → 技能(Skill)
```
关键设计决策:
1. **原子性**: 每个本能只描述一个行为,带信心分数 (0.3-0.9)
2. **项目隔离**: 用 git remote URL hash 作命名空间,防止跨项目污染
3. **渐进提升**: 单项目本能 → 多项目验证(2+项目, 信心>=0.8) → 全局技能
4. **可逆性**: `/evolve` 生成的技能可以回退到本能级别
这本质上是一个**强化学习循环** — 用户的接受/拒绝作为奖励信号,信心分数作为 Q-value 近似。与传统 fine-tuning 不同,它在推理时(通过 context injection而非训练时改变行为成本低且可控。
---
## Related
- [[Everything Claude Code 方法论与最佳实践]]
- [[Hook驱动优于提示词驱动]]