Tuning the Stochastic Machine: A Systems Engineer's Operating Model for Human-AI Engineering· 调优随机机器：人-AI 工程的操作模型
When an expert corrects an LLM assistant's error, the correction usually dies with the session, and the error class returns. I argue this is an operations problem, not a tooling problem: mechanisms for persisting corrections exist and are shipping, but the discipline for governing them -- versioning with provenance, recurrence monitoring, counter-metrics, retirement of stale rules -- does not. Writing as a systems engineer of thirty years, I map the LLM stack onto the machines my profession already operates (frozen silicon, firmware, loadable modules, persistent configuration, volatile memory), identify where the mapping fails (stochastic generation, configuration that binds only probabilistically, no general-purpose retirement (verification) stage by default), and derive from the failures
人-AI 工程需要操作模型来解决错误纠正的持续性问题。
- 核心方法
- 作者将 LLM 的架构映射到传统系统工程中的概念（如冻结合成、固件、可加载模块等），并识别出映射中的失败点，包括随机生成、仅概率绑定的配置和缺乏通用的验证阶段。
- 适合谁读
- 系统工程研究者、AI 工程师、人机交互设计师
- 要解决的问题
- 专家对大语言模型（LLM）助手的错误纠正往往不具有持久性，导致同一类错误反复出现。
- 关键实验
- 未提供
- 主要贡献
- 提出了一种系统工程的操作模型，用于管理和持久化 LLM 的错误纠正机制，包括版本控制、错误监测、反向指标和过时规则的退役。
- 意义与局限
- 该模型有助于提高人-AI 交互系统的可靠性，但需要进一步的研究和实践验证。