Files
nexus/wiki/concepts/Reliability-Engineering.md

33 lines
1.0 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
---
title: "Reliability Engineering"
type: concept
tags: []
sources:
- multi-agent-system-reliability
last_updated: 2026-04-28
---
# Reliability Engineering
## 定义
可靠性工程——将LLM视为分布式系统中不可靠组件的工程哲学而非"有感知"的智能体。
## 核心原则
停止要求模型"小心",开始**强制**其正确:
1. **Constrained约束**:通过架构约束(如依赖图强制执行)而非提示词约束
2. **Verified验证**:每个步骤有检查点,不合格则退回
3. **Pruned修剪**淘汰表现最差的Agent
4. **Challenged挑战**:通过对抗辩论让错误暴露
## 核心转变
从"AI原型"Prototype AI到"企业级AI"Enterprise AI的范式转变
- ❌ 将LLM视为神奇的聊天机器人
- ✅ 将LLM视为不可靠的分布式组件
## 关键人物
- [[Alex Ewerlöf]]可靠性工程专家KTH系统工程硕士27年经验专注将人类系统协作模式迁移至AI架构
## 来源
- [[multi-agent-system-reliability]]