嗯，用户让我帮忙总结一篇文章，控制在一百个字以内，而且不需要用“文章内容总结”这样的开头。好的，首先我需要理解这篇文章的主要内容。 文章标题是“确保你告诉AI你想做什么，而不是怎么做”，日期是2026年4月14日。内容主要讲的是 Harness Engineering 的正确和错误做法。Harness Engineering 是指如何正确使用AI，避免过度控制AI的执行过程。 文章提到 Bitter Lesson Engineering，这是来自Richard Sutton的“Bitter Lesson”论文。核心思想是不要试图比AI更聪明，不要微管理AI，而是明确告诉AI你想要的结果。坏的Harness Engineering会给出很多具体的步骤，比如先复制这个文件，然后加载这个等等。而好的做法则是提供大量的上下文信息，比如你是谁，你在做什么项目，你的目标是什么，以及什么是好的结果和坏的结果。 坏的做法的问题在于随着AI变得越来越智能，这些具体的指令会变得过时，甚至可能让AI变得更笨。而好的做法则因为无论AI多智能，只要它理解了你的需求和偏好，就能更好地为你服务。 总结起来就是：在使用AI时，应该关注于描述自己是谁、目标是什么、理想的结果是什么，并提供所需的工具和空间让AI去完成任务。而不是详细说明每一步该怎么做。 所以，在总结的时候需要涵盖这些要点： Harness Engineering 的正确与错误方法、Bitter Lesson Engineering 的概念、好坏做法的区别及其影响。 </think> 文章讨论了 Harness Engineering 的正确与错误方法。正确的做法是通过提供上下文信息（如身份、目标和偏好）来引导 AI 实现目标；错误的做法则是通过详细指令来控制 AI 的具体操作。前者随着 AI 智能提升仍有效果；后者则可能使 AI 变得低效甚至愚蠢。 2026-4-14 19:2:54 Author: danielmiessler.com(查看原文) 阅读量:19 收藏
Make sure you are telling your AI what you want and not how to get it
April 14, 2026
There is a right and wrong way to do Harness Engineering.
What makes it right or wrong mostly comes down to whether you're following the lessons of Bitter Lesson Engineering or not.
Bitter Lesson Engineering comes from Richard Sutton's "Bitter Lesson" essay, and it means ensuring that you're not trying to outsmart your own AI. It means not trying to micromanage how your AI does things, but rather specifying what you want done.
Plainly stated:
- Bad Harness Engineering is a whole bunch of prescriptive instructions on exactly how to do things.
First copy this file, then load this, then do this, then do that. Etc.
- Good Harness Engineering is about providing tons of context about who you are, what you're about, what you're working on, what you're trying to accomplish, and what good (and bad) look like to you.
I'm an engineer focused on personal productivity, I like simple designs with lots of whitespace and great typography, here are my previous projects, here are some tools you can use, etc.
Bad Harness Engineering is bad because the smarter AI gets the more antiquated your instructions will become. And at some point (maybe even now?) they'll make your AI stupider instead of smarter.
Good Harness Engineering is good because no matter how smart an AI becomes it will still be better at getting you great results if it understands who you are and what you like.
Basically, both your prompts and your harness should be about who you are and what you're trying to accomplish, and not specifically how to get there. That's what the AI is there to figure out.
Give it the best possible picture of you, your ideal outcome, and the best tools you can, and give it room to work.
如有侵权请联系:admin#unsafe.sh