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/Zero-Shot-Chain-of-Thought.md
+4 -4
View File
@@ -1,12 +1,12 @@
---
id: [[P-Reinforce]]-AUTO-ZSCOT-001
id: [[P-Reinforce|P-Reinforce]]-AUTO-ZSCOT-001
category: "10_Wiki/💡 Topics/AI"
confidence_score: 0.98
tags: [auto-reinforced, zero-shot-cot, chain-of-thought, [[Reasoning]], [[prompt]]ing, llm]
tags: [auto-reinforced, zero-shot-cot, chain-of-thought, [[Reasoning|Reasoning]], prompting, llm]
last_reinforced: 2026-04-20
---
# [[Zero-Shot-Chain-of-Thought]]
# [[Zero-Shot-Chain-of-Thought|Zero-Shot-Chain-of-Thought]]
## 📌 한 줄 통찰 (The Karpathy Summary)
> "마법의 주문 '차근차근 생각해보자': 복잡한 문제에 대해 결과를 바로 묻지 않고 생각의 과정을 요구함으로써, AI의 논리 회로를 강제로 활성화해 정답률을 드라마틱하게 높이는 추론 최적화 기폭제."
@@ -28,6 +28,6 @@ last_reinforced: 2026-04-20
- **정책 변화(RL Update)**: 엔터프라이즈 AI 솔루션 정책 수립 시, 답변의 정확도와 투명성을 높이기 위해 모든 AI 응답에 Zero-Shot-CoT를 기본 적용하여 '사고의 근거'를 함께 출력하게 하는 '과정 중심 응답 정책'이 확대됨.
## 🔗 지식 연결 (Graph)
- [[Prompt-Engineering]], [[Zero Shot and Few Shot Learning]], [[Thought-Architecture]], [[Decision Theory]], [[Self-Correction Mechanisms]]
- [[Prompt-Engineering|Prompt-Engineering]], [[Zero Shot and Few Shot Learning|Zero Shot and Few Shot Learning]], [[Thought-Architecture|Thought-Architecture]], [[Decision Theory|Decision Theory]], Self-Correction Mechanisms
- **Modern Tech/Tools**: OpenAI o1 model (Internal CoT), LangChain advanced chains.
---