AI时代的神话人物万梦
上个周末我看到四个人拼命地想要把笔记本电脑连接到屏幕上我欣然观察他们的努力无意加入
但有人逼我：你不能看看吗？
我回答："哈哈，对不起，不！我的经验是，增加更多的人不会更快地解决这个问题。”
我当然是 -- -- 间接 -- -- 回到布鲁克斯的律法：
"把人力加到一个晚期的软件项目上会让它更晚".
它由计算机科学家小弗雷德里克·P·布鲁克斯(英语：Frederick P. Brooks Jr.)根据其管理IBM OS/360项目的经验，在其1975年的著作"神话人物-蒙斯"中制定。
不管怎样，我总得想想这在AI agents和LLMs的年代是否仍然维持？
一开始，传统的瓶颈——登机时间，无休止的站立和办公政治——一夜之间就消失了。 AI agent在毫秒内达到速度，不需要咖啡休息。
但当你仔细看法律并没有消失它只是变异。
著名的“婴儿问题”依然存在：9个agents仍无法在一个月内分娩。 顺序任务仍依次进行。
超头并没有消失；它转移了：你现在不是在管理人，而是在管理agents. 仍然有人需要定义"done"，审查代码，捕捉幻觉，将碎片缝合在一起。
那个人就是你
将9个自主的agents扔到一个没有晶体清澈的管弦乐的单一密码库，他们将愉快地在高速环路中重写对方的作品。
也许2026年更新的布鲁克斯法律应该是：
"把agents加到一个要求不明确的项目上，会更快地得到错误的答案".
本文由 AI图鉴自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
The Mythical Man-Month in the age of AI
Last weekend I watched four people desperately trying to get a laptop to connect to a screen. I was happily observing their efforts, with zero intent to join in.
But someone nudged me: can't you have a look at it?
My reply: "Haha sorry no! My experience is that adding more people will not solve this problem any quicker".
I was of course -- indirectly -- reffering to Brooks's Law:
"Adding manpower to a late software project makes it later."
It was formulated by computer scientist Frederick P. Brooks Jr. in his 1975 book The Mythical Man-Month, based on his experience managing the IBM OS/360 project.
However I got to thinking. Does this still hold up in the age of AI agents and LLMs?
At first glance, you’d think no. The traditional bottlenecks -- onboarding time, endless stand-ups, and office politics -- disappear overnight. An AI agent is up to speed in milliseconds and doesn't demand a coffee break.
But when you look closer, and the law hasn't vanished. It just mutated.
The famous "Baby Problem" remains: nine agents still can’t deliver a baby in one month. Sequential tasks are still sequential.
Overhead hasn't disappeared; it shifted: instead of managing people, you are now managing agents. Someone still needs to define "done", review the code, catch hallucinations, and stitch the pieces together.
That someone is you.
Throw nine autonomous agents at a single codebase without crystal-clear orchestration, and they will happily rewrite each other's work in a high-speed loop.
Maybe the 2026 update to Brooks’s Law should be:
"Adding agents to a project with unclear requirements gets you the wrong answer faster."
Auto-fetched and translated by AI Atlas. All rights belong to the original author.