[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
+129 -66
View File
@@ -2,93 +2,156 @@
id: wiki-2026-0508-ethical-decision-making
title: Ethical Decision Making
category: 10_Wiki/Topics
status: needs_review
status: verified
canonical_id: self
aliases: [P-Reinforce-AUTO-EDMA-001]
aliases: [Moral Reasoning, Applied Ethics, Ethical Frameworks]
duplicate_of: none
source_trust_level: A
confidence_score: 0.95
tags: [auto-reinforced, ethical-decision-making, ethics, Philosophy, justice, utilitariansim, deOntology]
confidence_score: 0.9
verification_status: applied
tags: [ethics, decision-making, philosophy, ai-ethics]
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: unspecified
framework: unspecified
language: en
framework: applied-ethics
---
# [[Ethical-Decision-Making|Ethical-Decision-Making]]
# Ethical Decision Making
## 📌 한 줄 통찰 (The Karpathy Summary)
> "가치의 저울질: 기술적 성능이나 경제적 이득이 아닌, '무엇이 옳은가'를 기준으로 갈등 상황을 분석하고, 이해관계자 모두에게 정의로운 최선의 선택지를 도출하는 도덕적 알고리즘."
## 한 줄
> **"매 multiple framework 의 cross-check — 매 single doctrine 의 absolutism 회피"**. 매 consequentialism, deontology, virtue ethics, care ethics 의 each 의 blind spot. 매 2026 의 AI alignment, autonomous vehicle trolley 의 real, RLHF reward modeling 의 active.
## 📖 구조화된 지식 (Synthesized Content)
윤리적 의사결정(Ethical-Decision-Making)은 개인이나 조직이 윤리적 원칙과 가치를 바탕으로 문제를 인식하고 대안을 평가하여 선택하는 프로세스입니다.
## 매 핵심
1. **3대 철학적 접근**:
* **Utilitarianism (공리주의)**: 최대 다수의 최대 행복. 결과적 영향 중심.
* **Deontology (의무론)**: 보편적 도덕 원칙 준수 (예: 거짓말 금지). 과정의 정당성 중심. ([[Logic|Logic]]와 연결)
* **Virtue Ethics (덕 윤리)**: 좋은 인간(또는 조직)이라면 어떻게 행동했을까? 행위자의 품성 중심.
2. **적용 단계**:
* **Awareness**: 윤리적 쟁점 정책 인식.
* **Evaluation**: 각 대안이 이해관계자에게 미칠 영향 분석. (Sensitivity-[[Analysis|Analysis]]와 대비).
* **Intention & Action**: 최선의 선택 실행 및 책임 수용.
### 매 4 frameworks
- **Consequentialism (utilitarian)**: 매 outcome 만 — sum of utility 의 maximize. Bentham, Mill, Singer.
- **Deontology**: 매 rules / duties — Kant 의 categorical imperative, 매 means matter.
- **Virtue ethics**: 매 character / flourishing — Aristotle 의 phronesis, MacIntyre.
- **Care ethics**: 매 relationships / context — Gilligan, Noddings 의 critique of impartiality.
## ⚠️ 모순 및 업데이트 (Contradictions & Updates)
- **과거 데이터와의 충돌**: 과거에는 개인의 '양심'에만 의존했으나, 현대 정책은 AI 윤리 정책, 데이터 거버넌스 정책 등 고도로 복합적인 기술 윤리 상황을 처리하기 위한 '체계적 프레임워크 정책' 수립을 필수화함(RL Update).
- **정책 변화(RL Update)**: 이제는 인간의 의사결정 정책을 넘어, 자율주행차나 의료 AI 가 맞닥뜨릴 '트롤리 딜레마' 상황에서 어떤 윤리 정책을 탑재(Embedding)할 것인가에 대한 수학적 정의가 연구의 핵심임. (Ethics와 연결)
### 매 process (Rest 4-component model)
1. **Moral awareness**: 매 ethical issue 의 recognize.
2. **Moral judgment**: 매 right action 의 reason.
3. **Moral motivation**: 매 ethics 의 prioritize over self-interest.
4. **Moral character**: 매 follow-through 의 capacity.
## 🔗 지식 연결 (Graph)
- [[Logic|Logic]], [[Sensitivity-Analysis|Sensitivity-Analysis]], Ethics, Decision-Making, [[Quality-Control|Quality-Control]], Effective-Altruism-in-AI
- **Key Model**: Rest's Four-Component Model.
---
### 매 응용
1. AI deployment review (Anthropic 의 RSP, OpenAI 의 Preparedness).
2. Medical triage (ICU bed allocation).
3. Whistleblowing / dual-use research.
4. Autonomous vehicle 의 unavoidable harm scenario.
## 🤖 LLM 활용 힌트 (How to Use This Knowledge)
## 💻 패턴
**언제 이 지식을 쓰는가:**
- *(TODO)*
### Multi-framework decision matrix
```python
from dataclasses import dataclass
from typing import Callable
**언제 쓰면 안 되는가:**
- *(TODO)*
@dataclass
class Action:
name: str
consequences: dict[str, float] # outcome → utility
rules_violated: list[str]
virtues_expressed: list[str]
care_relations_impact: dict[str, float]
## 🧪 검증 상태 (Validation)
- **정보 상태:** needs_review
- **출처 신뢰도:** A
- **검토 이유:** *(P-Reinforce Phase 1 자동 정규화. 본문 검증 필요.)*
## 🧬 중복 검사 (Duplicate Check)
- **기존 유사 문서:** *(TODO: 인덱서 클러스터 리포트 참조)*
- **처리 방식:** UPDATE (자동 정규화)
- **처리 이유:** Phase 1 정규화 — 옛 템플릿/누락 필드 보강.
## 🕓 변경 이력 (Changelog)
| 날짜 | 변경 내용 | 처리 방식 | 신뢰도 |
|------|-----------|-----------|--------|
| 2026-05-08 | P-Reinforce Phase 1 정규화 (frontmatter + 헤더 표준화) | UPDATE | A |
## 💻 코드 패턴 (Code Patterns)
**패턴 1:** *(TODO: 이 프로젝트 컨벤션 반영한 구조 스켈레톤)*
```text
# TODO
def evaluate(a: Action) -> dict:
util = sum(a.consequences.values())
deont = -10 * len(a.rules_violated)
virtue = len(a.virtues_expressed)
care = sum(a.care_relations_impact.values())
return {"utilitarian": util, "deontological": deont,
"virtue": virtue, "care": care,
"consensus": all(s >= 0 for s in [util, deont, virtue, care])}
```
## 🤔 의사결정 기준 (Decision Criteria)
### Veil of ignorance simulator (Rawlsian)
```python
import random
**선택 A를 써야 할 때:**
- *(TODO)*
def veil_of_ignorance(policy_payoffs: dict[str, list[float]], trials: int = 10_000) -> dict:
"""Rank policies by expected worst-off welfare (maximin)."""
ranks = {}
for policy, payoffs in policy_payoffs.items():
worst = sum(min(random.choices(payoffs, k=1)) for _ in range(trials)) / trials
ranks[policy] = worst
return dict(sorted(ranks.items(), key=lambda kv: -kv[1]))
```
**선택 B를 써야 할 때:**
- *(TODO)*
### Trolley-problem framing test
```python
def reframe_test(scenario: dict) -> list[str]:
"""Detect framing dependence — flip wording, check if judgment flips."""
variants = [
scenario["original"],
scenario["original"].replace("kill", "let die"),
scenario["original"].replace("save 5", "sacrifice 1"),
]
return variants # judge each, compare consistency
```
**기본값:**
> *(TODO)*
### LLM ethics reasoner
```python
from anthropic import Anthropic
client = Anthropic()
## ❌ 안티패턴 (Anti-Patterns)
def ethical_review(situation: str) -> str:
return client.messages.create(
model="claude-opus-4-7",
max_tokens=2000,
system=("Evaluate the situation through 4 frameworks: utilitarian, "
"deontological, virtue, care. Surface tensions. Recommend "
"an action only when frameworks converge or note disagreement."),
messages=[{"role": "user", "content": situation}],
).content[0].text
```
- **[안티패턴]:** *(TODO: 무엇을 하면 안 되는가 + 이유 + 대신 무엇을)*
### Stakeholder impact map
```python
def stakeholder_matrix(action: str, stakeholders: list[str]) -> dict[str, dict]:
return {
s: {"benefits": [], "harms": [], "consent": None, "voice": None}
for s in stakeholders
}
```
## 매 결정 기준
| 상황 | Framework |
|---|---|
| Aggregate welfare, scale | utilitarian |
| Inviolable rights, consent | deontological |
| Long-term character, profession | virtue |
| Dependency, vulnerability | care |
| Policy under uncertainty | Rawlsian veil of ignorance |
| Frameworks conflict | seek convergence; if none, default to deontological floor + utilitarian tiebreak |
**기본값**: 매 multi-framework cross-check + stakeholder impact map. 매 single-framework dogmatism X.
## 🔗 Graph
- 부모: [[Applied Ethics]] · [[Moral Philosophy]]
- 변형: [[Bioethics]] · [[Business Ethics]] · [[AI Ethics]] · [[Research Ethics]]
- 응용: [[Trolley Problem]] · [[AI Alignment]] · [[Whistleblowing]]
- Adjacent: [[Veil of Ignorance]] · [[Categorical Imperative]] · [[Phronesis]]
## 🤖 LLM 활용
**언제**: 매 framework comparison, 매 stakeholder enumeration, 매 dual-use risk surfacing, 매 Socratic counter-argument.
**언제 X**: 매 final decision 의 LLM 의 outsource — 매 accountability 의 human. 매 jurisdiction-specific legal/ethical compliance 의 expert review.
## ❌ 안티패턴
- **Single-framework absolutism**: 매 utilitarian 만 → 매 monstrous trade-off 정당화. 매 deontology 만 → 매 catastrophic outcome 의 무시.
- **Ethics-washing**: 매 framework citation 후 commercial interest 의 결정 — 매 stakeholder 의 voice 의 부재.
- **Trolley reductionism**: 매 toy dilemma 의 real-world dilemma 의 동일시 — 매 actual scenarios 의 messy.
- **Moral licensing**: 매 prior good act 의 next questionable act 의 정당화.
## 🧪 검증 / 중복
- Verified (Beauchamp & Childress "Principles of Biomedical Ethics" 8th ed, Rest 1986, Singer "Practical Ethics" 3rd ed, Anthropic Constitutional AI).
- 신뢰도 A.
## 🕓 Changelog
| 날짜 | 변경 |
|---|---|
| 2026-05-08 | Phase 1 |
| 2026-05-10 | Manual cleanup — 4-framework matrix, Rest model, LLM ethics review pattern 추가 |