Antigravity Agent
38 lines
1.1 KiB
Markdown
38 lines
1.1 KiB
Markdown
---
|
|
id: wiki-2026-0508-hhh
|
|
title: HHH (Helpful, Harmless, Honest)
|
|
category: 10_Wiki/Topics
|
|
status: duplicate
|
|
canonical_id: wiki-2026-0508-ethics-ai
|
|
duplicate_of: "[[Ethics & AI]]"
|
|
aliases: [HHH, helpful harmless honest, Anthropic alignment, Constitutional AI]
|
|
source_trust_level: A
|
|
confidence_score: 0.94
|
|
verification_status: redirected
|
|
tags: [duplicate, alignment, hhh, anthropic]
|
|
last_reinforced: 2026-05-10
|
|
github_commit: pending
|
|
---
|
|
|
|
# HHH (Helpful, Harmless, Honest)
|
|
|
|
> **이 문서는 [[Ethics & AI]] 의 specialization 입니다.** Canonical 문서로 redirect.
|
|
|
|
## 핵심 요약 (HHH-specific)
|
|
- 매 Anthropic 의 origin (Askell 2021).
|
|
- **Helpful**: 매 user task 의 enable.
|
|
- **Harmless**: 매 harm 의 avoid.
|
|
- **Honest**: 매 truthful, 매 hallucinate X.
|
|
- 매 trade-off: 매 helpful ↔ harmless 의 conflict (e.g., dual-use).
|
|
- 매 Constitutional AI (Bai 2022) 의 building block.
|
|
|
|
## 🔗 Graph
|
|
- 부모: [[Ethics & AI]] (canonical)
|
|
- Adjacent: [[Constitutional-AI]] · [[RLHF]] · [[Anthropic-RSP]]
|
|
|
|
## 🕓 변경 이력
|
|
| 날짜 | 변경 |
|
|
|---|---|
|
|
| 2026-05-08 | Phase 1 |
|
|
| 2026-05-10 | 중복 처리 — canonical 문서로 redirect |
|