命令 (command)
集里怎么说它
- 《Heitor:用智能体重塑软件工程工作流的实操蓝图》(31:30起):本集区分命令与技能:命令是人主动调用的,能保证指令被遵循;技能是模型自主触发的,容易被跳过或曲解。本集工作流中的 slash roadmap、slash retro 等都是命令
① 提到它的金句
9 条
Bash 本质上是相当危险的,并且它能以意想不到的方式改变系统状态。但与此同时如果你必须手动批准每一条 bash 命令,作为一名工程师这超级烦人,而且你无法真正提高生产力,因为你只是在不断地批准每一条命令。
指向原始笔记的链接
Bash is inherently pretty dangerous and it can change system state in unexpected ways. But at the same time if you have to manually approve every single bash command, it’s super annoying as an engineer, and you can’t really be productive because you’re just constantly approving every command.
—— Boris · [24:21]
我通常寻找对这门学科的明显掌控,但还要有品味,能说:“嘿,你要拥有无限的 token,我们不能只是在制造垃圾。”
指向原始笔记的链接
I generally look for obviously command over the discipline, but then the taste to say, “Hey, you’re going to have unlimited tokens and we can’t just be doing slop.”
—— Andrew Ambrosino · [31:20]
像一些价值,一些公司可能会亏钱,但它们会达到一个可以指挥巨大价值转移的位置。
指向原始笔记的链接
Like some value, some companies may lose money, but they’ll get to a position where they can command a tremendous transfer of value.
—— Martin Casado · [10:41]
攻击一个仓库所需的知识量,基本上就是:你能在你的终端里运行一条 shell 命令吗,对吧?
指向原始笔记的链接
The amount of knowledge needed to attack a repository is basically can you run a shell command in your terminal, right?
—— 嘉宾 · [25:01]
(被动护栏)胜过一条没人记得去运行的命令。
指向原始笔记的链接
Beat a command no one remembers to run.
—— Paul Bakaus · [32:34]
所以我们正在重新思考:如何把最初的第一人称操控模式,转换成一种更具战略性的多智能体视图,让你可以带着一个目标指挥整个机队,而不用担心飞行本身。
指向原始笔记的链接
So we’re kind of rethinking as to what this means in terms of this initial first-person viewing engagement with these systems to how do we convert this to a most strategic multi-agent view that you can kind of command the entire fleet with an objective in mind without having to worry about the flight.
—— Suchet Bargoti · [08:26]
我选择的智能体可以按需创建任何我想要的应用,哪怕这个应用只有我一个人用。
指向原始笔记的链接
The agent of my choosing can create any app that I want on command, even if that app is only for me.
—— Ben Thompson · [09:17]
这是我所知道的唯一一个命令,不仅安装一个技能,还免费附赠提示词注入。
指向原始笔记的链接
That’s the only command I know that installs not just a skill, but also free prompt injections,
—— Rafal Wilinski · [06:14]
这里另一个有趣的事实是,如果你看到智能体一遍又一遍地犯同样的错误,多次调用错误的命令,考虑把那个(错误的)用法变成你的契约。
指向原始笔记的链接
And another interesting fact here is if you see agents making the same mistake over and over, calling the wrong command a bunch of times, consider making that your contract.
—— Pedro Lopez · [13:23]
② 出现在这些集
1 集
- 《Heitor:用智能体重塑软件工程工作流的实操蓝图》 — 作为概念
③ 关联
点进去有真内容 —— 本页主要出口
Heitor Lessa · 智能体 · 规范驱动开发 · 苏格拉底方法 · 对抗性审查 · 合并检查 · 技能 · 确定性 · 伪造证据 · 三层模型分层
