# 最小化 harness 才是长期最优解

- 来源：elvis (@omarsar0)
- 发布时间：2026-08-30 23:10
- AIHOT 分数：46
- AIHOT 链接：https://aihot.virxact.com/items/cmtfyf36k02h4ro3xzativqda
- 原文链接：https://x.com/omarsar0/status/2094080366919188843

## AI 摘要

Elvis Saravia 推荐一篇观点文章，称自己越来越倾向使用 Pi 这类极简 harness，以便在模型间轻松切换而不牺牲性能。他提醒，在模型快速迭代的当下，应谨慎选择优化目标和方式。引用推文指出，像 Oh My Pi 这类捆绑大量技巧的复杂 harness 虽在基准上表现好，但每次模型发布都可能使结果失效，而极简配置会随更强模型出现而持续受益。

## 正文

Recommended read. It's an opinion, but increasingly I find myself doing the same.

I've optimized for using minimal harnesses like Pi and have found it easier to switch to newer models or alternate between open and closed ones without sacrificing performance.

Be careful what you optimize for and how you do it, especially with the velocity of things today.

And if you are hardcore like I prefer, build and optimize your own harness and set up evals and loops to optimize the setup autonomously.

### 引用推文

> Kun Chen：while maintaining my open source projects i noticed many people started using something called Oh My Pi out of curiosity i took a look and gave it a go myself, ...