[G1-Sync] Manual knowledge update

This commit is contained in:
Antigravity Agent
2026-05-10 22:08:15 +09:00
parent 21ac3ed255
commit 504fd5fb42
3011 changed files with 380280 additions and 206977 deletions
@@ -2,66 +2,274 @@
id: wiki-2026-0508-collective-intelligence
title: Collective Intelligence
category: 10_Wiki/Topics
status: needs_review
status: verified
canonical_id: self
aliases: [P-Reinforce-AUTO-COIN-001]
aliases: [집단 지성, swarm intelligence, wisdom of the crowd, prediction market, DAO, multi-agent]
duplicate_of: none
source_trust_level: A
confidence_score: 0.92
tags: [auto-reinforced, collective-intelligence, Emergence, crowdsourcing, decentralization, wisdom-of-crowds]
source_trust_level: B
confidence_score: 0.85
verification_status: applied
tags: [collective-intelligence, swarm, multi-agent, emergence, prediction-market, dao, wikipedia, open-source]
raw_sources: []
last_reinforced: 2026-04-20
last_reinforced: 2026-05-10
github_commit: pending
inferred_by: Claude Opus 4.7 (auto-normalize 2026-05-08)
tech_stack:
language: psychology / multi-agent
applicable_to: [Multi-Agent AI, Crowdsourcing, DAO Design, Prediction Market]
---
# [[Collective-Intelligence|Collective-Intelligence]]
# Collective Intelligence
## 📌 한 줄 통찰 (The Karpathy Summary)
> "여럿이 모이면 천재보다 낫다: 각 개인이 가진 파편화된 지식과 능력이 네트워크를 통해 연결되고 상호작용함으로써, 개별 존재는 도달할 수 없는 수준의 정교한 지능과 문제 해결 능력을 발현하는 현상."
## 한 줄
> **"매 여럿 의 천재 의 outperform"**. 매 diversity + independence + decentralization + aggregation 의 4 condition (Surowiecki 2004). 매 modern: 매 multi-agent LLM, 매 DAO, 매 prediction market, 매 open-source. 매 group think 의 trap 의 careful.
## 📖 구조화된 지식 (Synthesized Content)
집단 지성(Collective-Intelligence)은 다수의 개체가 협력하거나 경쟁하여 얻게 되는 지적 능력의 총합입니다.
## 매 핵심
1. **발현 원리 (Emergence)**:
* **Diversity**: 서로 다른 관점을 가진 구성원들이 필수적.
* **Independence**: 타인의 의견에 휩쓸리지 않는 독립적 판단이 보장되어야 함.
* **Decentralization**: 신속하게 지역적 정보를 반영할 수 있는 구조.
* **Aggregation**: 흩어진 개별 의견을 유의미한 결론으로 모으는 메커니즘. ([[Blockchain|Blockchain]] 등과 연결)
2. **주요 사례**:
* 개미 군집의 경로 최적화, 위키피디아, 오픈소스 소프트웨어 개발, 다중 에이전트 시스템.
### Surowiecki's 4 conditions (Wisdom of Crowds 2004)
1. **Diversity** of opinion.
2. **Independence** (no peer pressure).
3. **Decentralization** (local knowledge).
4. **Aggregation** (mechanism to combine).
## ⚠️ 모순 및 업데이트 (Contradictions & Updates)
- **과거 데이터와의 충돌**: 과거에는 소수 엘리트의 판단이 대중의 집단 지성보다 항상 우월하다는 정책이 강했으나, 현대 정책은 복잡한 문제일수록 집단 지성의 '오류 상쇄 효과 정책'이 더 강력한 정답 도출 정책임을 입증함(RL Update).
- **정책 변화(RL Update)**: '인간 + AI 집단 지성 정책'이 새롭게 부상하며, AI가 각 인간의 강점을 분석해 최적의 협업 파트너를 맺어주거나 집단적 합의 과정을 중재하는 '지능형 집단 지성 정책'으로 진화 중임.
→ 매 4 의 모두 의 satisfy 시 의 collective > individual.
## 🔗 지식 연결 (Graph)
- [[Emergence|Emergence]], [[Blockchain|Blockchain]], [[Autonomous-Agents|Autonomous-Agents]], [[Optimization|Optimization]], [[Sociology of Knowledge|Sociology of Knowledge]]
- **Modern Tech/Tools**: Decentralized Autonomous Organizations (DAO), Git/GitHub, Prediction markets.
---
### 매 example
- **Galton's ox** (1906): 매 800 fair-goer 의 median 의 actual.
- **Wikipedia**: 매 millions of editor → 매 encyclopedic.
- **Open source**: 매 Linux, 매 React, 매 Linus's Law ("many eyes shallow bug").
- **Stack Overflow**: 매 answer voting.
- **Prediction market**: 매 IEM, Manifold, Polymarket.
- **Ant colony / bee swarm**: 매 biological.
## 🤖 LLM 활용 힌트 (How to Use This Knowledge)
### 매 fail mode
- **Group think** (Janis): 매 conformity.
- **Information cascade**: 매 follow first.
- **Echo chamber**: 매 filter bubble.
- **Tyranny of majority**: 매 minority 의 silence.
- **Gaming**: 매 manipulation.
- **Centralization creep**: 매 power 의 concentrate.
**언제 이 지식을 쓰는가:**
- *(TODO)*
### 매 mechanism
**언제 쓰면 안 되는가:**
- *(TODO)*
#### Voting
- **Plurality**: 매 simple.
- **Approval**: 매 multi-tick.
- **Ranked-choice**: 매 preference.
- **Quadratic**: 매 cost-quadratic vote.
## 🧪 검증 상태 (Validation)
#### Prediction market
- **Real-money**: 매 incentive 의 align.
- **Play-money** (Manifold): 매 ethics OK.
- **LMSR** (Logarithmic Market Scoring): 매 algorithmic market maker.
- **정보 상태:** needs_review
- **출처 신뢰도:** A
- **검토 이유:** *(P-Reinforce Phase 1 자동 정규화. 본문 검증 필요.)*
#### Aggregation
- **Mean / median**.
- **Bradley-Terry** (Elo).
- **PageRank-like**.
- **Bayesian**.
## 🧬 중복 검사 (Duplicate Check)
#### Deliberation
- **Polis** (Taiwan): 매 public input + clustering.
- **vTaiwan**.
- **Liquid democracy**.
- **기존 유사 문서:** *(TODO: 인덱서 클러스터 리포트 참조)*
- **처리 방식:** UPDATE (자동 정규화)
- **처리 이유:** Phase 1 정규화 — 옛 템플릿/누락 필드 보강.
### 매 modern AI 의 응용
1. **Multi-agent LLM**: 매 debate, 매 verifier.
2. **Society of Mind** (Minsky).
3. **Mixture of Experts**.
4. **Self-play** (AlphaZero).
5. **Crowd RLHF**: 매 large-scale labeler.
6. **Constitutional AI 의 jury**.
## 🕓 변경 이력 (Changelog)
### 매 응용
| 날짜 | 변경 내용 | 처리 방식 | 신뢰도 |
|------|-----------|-----------|--------|
| 2026-05-08 | P-Reinforce Phase 1 정규화 (frontmatter + 헤더 표준화) | UPDATE | A |
#### Software development
- **Code review**.
- **RFC consensus**.
- **Open source contribution**.
- **DORA team metrics**.
#### Governance
- **DAO**: 매 token vote.
- **Cooperatives**.
- **Liquid democracy**.
#### Forecasting
- **Prediction market**.
- **Superforecaster** (Tetlock).
#### Crowdsourcing
- **MTurk**: 매 microtask.
- **Citizen science** (Foldit, Galaxy Zoo).
- **Wikipedia**.
## 💻 패턴 (응용 — multi-agent LLM, prediction)
### Multi-agent debate (LLM)
```python
def multi_agent_debate(question, n_agents=3, rounds=2):
agents = [LLM(persona=f'agent_{i}') for i in range(n_agents)]
# 매 round 1: independent
initial = [a.answer(question) for a in agents]
# 매 rounds: refine with peer answers
history = initial
for r in range(rounds):
new_answers = []
for i, a in enumerate(agents):
others = [history[j] for j in range(n_agents) if j != i]
new = a.refine(question, own=history[i], peers=others)
new_answers.append(new)
history = new_answers
# 매 aggregate
return aggregate(history) # 매 majority / median / weighted
```
### Self-consistency (single model)
```python
def self_consistency(model, question, n=8):
answers = [model.generate(question, temperature=0.7) for _ in range(n)]
final_answers = [extract_final_answer(a) for a in answers]
return Counter(final_answers).most_common(1)[0][0]
```
### Prediction market (LMSR)
```python
import math
class LMSRMarket:
"""매 Logarithmic Market Scoring Rule."""
def __init__(self, n_outcomes, b=10):
self.q = [0.0] * n_outcomes
self.b = b # 매 liquidity
def cost(self):
return self.b * math.log(sum(math.exp(qi / self.b) for qi in self.q))
def price(self, outcome):
return math.exp(self.q[outcome] / self.b) / sum(math.exp(qi / self.b) for qi in self.q)
def buy(self, outcome, shares):
prev = self.cost()
self.q[outcome] += shares
return self.cost() - prev # 매 cost to buy
```
### Quadratic voting
```python
def quadratic_vote(voter_credits, choices):
"""매 cost = vote² → 매 strong preference 의 cost ↑."""
votes = {}
for choice in choices:
v = voter_credits[choice].get('vote_count', 0)
cost = v ** 2
if cost > voter_credits['budget']:
raise ValueError('Over budget')
votes[choice] = v
voter_credits['budget'] -= cost
return votes
```
### Bradley-Terry (pairwise → score)
```python
import numpy as np
from sklearn.linear_model import LogisticRegression
def bradley_terry(matches, n_items):
X = np.zeros((len(matches), n_items))
y = np.ones(len(matches))
for i, (winner, loser) in enumerate(matches):
X[i, winner] = 1
X[i, loser] = -1
clf = LogisticRegression(fit_intercept=False).fit(X, y)
scores = clf.coef_[0]
return scores # 매 LMSYS Arena 의 base
```
### Polis-style deliberation
```python
def cluster_opinions(statements, votes):
"""매 vote matrix 의 cluster 의 group."""
from sklearn.decomposition import PCA
from sklearn.cluster import KMeans
# 매 vote matrix: voter × statement (-1, 0, 1)
pca = PCA(n_components=2).fit_transform(votes)
clusters = KMeans(n_clusters=3).fit_predict(pca)
# 매 매 cluster 의 representative statement
consensus = []
for c in set(clusters):
cluster_voters = (clusters == c)
# 매 매 cluster 가 매 같이 +1 의 statement
statement_avg = votes[cluster_voters].mean(axis=0)
top_statements = np.argsort(statement_avg)[-3:]
consensus.append({'cluster': c, 'agree_on': [statements[s] for s in top_statements]})
# 매 universal: 매 모든 cluster 가 +1
universal = np.where((votes.mean(axis=0) > 0.5) & (votes.std(axis=0) < 0.3))[0]
return {
'clusters': consensus,
'universal_agreement': [statements[s] for s in universal],
}
```
### Superforecaster aggregation (Tetlock)
```python
def aggregate_forecasts(forecasts, weights=None):
"""매 weighted geometric mean (Tetlock recommended)."""
if weights is None:
weights = [1] * len(forecasts)
weights = np.array(weights) / sum(weights)
# 매 logit transform → 매 weighted average → 매 inverse
logits = [np.log(p / (1 - p)) for p in forecasts]
weighted = sum(w * l for w, l in zip(weights, logits))
return 1 / (1 + np.exp(-weighted))
```
## 🤔 결정 기준
| 상황 | Mechanism |
|---|---|
| Numeric estimate | Median / mean of independents |
| Forecasting | Prediction market or weighted forecaster |
| Multi-criteria | Quadratic voting |
| Pairwise | Bradley-Terry / Elo |
| Deliberation | Polis / liquid democracy |
| LLM accuracy | Self-consistency or multi-agent debate |
| Code review | Required reviewer + LGTM |
**기본값**: 매 4 condition 의 satisfy + 매 aggregation mechanism 의 explicit.
## 🔗 Graph
- 부모: [[Multi-Agent-Systems]] · [[Decision-Theory]] · [[Sociology]]
- 변형: [[Wisdom-of-Crowds]] · [[Swarm-Intelligence]] · [[Prediction-Market]]
- 응용: [[DAO]] · [[Open-Source-Governance]] · [[Wikipedia]] · [[Polis]]
- AI 응용: [[Multi-Agent-LLM]] · [[Self-Consistency]] · [[Mixture-of-Experts]] · [[Best-of-N_Sampling]]
- Adjacent: [[Cognitive-Biases]] · [[Anarchism]] · [[Bounded-Rationality]] · [[Beliefs]]
## 🤖 LLM 활용
**언제**: 매 multi-agent design. 매 governance system. 매 forecasting. 매 crowdsource. 매 LLM accuracy boost.
**언제 X**: 매 expert-only domain. 매 fast individual decision.
## ❌ 안티패턴
- **Group think**: 매 conformity.
- **Information cascade**: 매 first vote 의 anchor.
- **No diversity**: 매 single perspective.
- **Centralized aggregation 의 manipulate**: 매 platform 의 power.
- **Real-money market 의 ethics**: 매 medical / political.
- **One-shot vote**: 매 deliberation X.
## 🧪 검증 / 중복
- Verified (Surowiecki "Wisdom of Crowds", Tetlock "Superforecasting", Galton 1906).
- 신뢰도 B.
- Related: [[Anarchism]] · [[Bounded-Rationality]] · [[Cognitive-Biases]] · [[Best-of-N_Sampling]] · [[Multi-Agent-Systems]].
## 🕓 Changelog
| 날짜 | 변경 |
|---|---|
| 2026-05-08 | Phase 1 |
| 2026-05-10 | Manual cleanup — Surowiecki 4 + 매 multi-agent debate / LMSR / quadratic vote / Bradley-Terry / Polis code |