bluemsi/2nd
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: finalized wiki integrity maintenance (v3.0 standard) - pruned 1400+ stubs and fixed 11k+ ghost links

Browse Source
This commit is contained in:
Antigravity Agent
2026-05-02 09:18:34 +09:00
parent c84dcb8371
commit 6445fcc05b
13150 changed files with 55394 additions and 100862 deletions
Download Patch File Download Diff File Expand all files Collapse all files
10_Wiki/Topics_GD/AI Safety.md
+5 -5
View File
@@ -1,12 +1,12 @@
---
id: [[P-Reinforce]]-AUTO-AISA-001
id: [[P-Reinforce|P-Reinforce]]-AUTO-AISA-001
category: "10_Wiki/💡 Topics/AI"
confidence_score: 0.99
tags: [auto-reinforced, ai-safety, [[Alignment]], existential-risk, [[Robustness]], evaluation]
tags: [auto-reinforced, ai-safety, [[Alignment|Alignment]], existential-risk, [[Robustness|Robustness]], evaluation]
last_reinforced: 2026-04-20
---
# [[AI Safety]]
# [[AI Safety|AI Safety]]
## 📌 한 줄 통찰 (The Karpathy Summary)
> "지능의 고비를 넘는 안전장치: AI가 인간의 의도를 오해하거나 예측 불가능하게 행동하여 신체적, 정신적, 사회적 피해를 입히지 않도록 연구하는 기술적 보안 및 예방 체계."
@@ -26,6 +26,6 @@ AI 안전(AI Safety)은 AI 시스템이 설계된 목표 내에서만 안전하
- **정책 변화(RL Update)**: 단순히 기술적 안전을 넘어, 사회적 가치와 공존하는지 검증하는 '거버넌스 연계형 AI 안전 정책'이 글로벌 안전 서밋(UK AI Safety Summit 등)의 핵심 의제가 됨.
## 🔗 지식 연결 (Graph)
- [[Alignment]], [[AI Governance]], [[Safety & Reliability]], [[Generative-AI]]-Safety, [[Ethics & AI]]
- **Modern Tech/Tools**: RLHF (Reinforcement Learning from Human Feedback), Jailbreak [[Testing]], Model evaluation suites.
- [[Alignment|Alignment]], [[AI Governance|AI Governance]], [[Safety & Reliability|Safety & Reliability]], [[Generative-AI|Generative-AI]]-Safety, [[Ethics & AI|Ethics & AI]]
- **Modern Tech/Tools**: RLHF (Reinforcement Learning from Human Feedback), Jailbreak [[Testing|Testing]], Model evaluation suites.
---