Andrew Qu
① 他说过的话
8 条
与其每张桌子上一台计算机, 我们能不能做到每张桌子上一个智能体?
指向原始笔记的链接
instead of a computer on every desk, could we potentially have an agent on every desk?
—— Andrew Qu · [02:05]
我们在一旁感叹: 哇, 和我们之前的东西相比, Claude Code 加 Opus 4.5 基本上就是 AGI 了。
指向原始笔记的链接
we on the side were like, wow, Claude Code and Opus 4.5 is basically AGI compared to what we had before.
—— Andrew Qu · [07:50]
我们意识到, 最大的解锁就是: 它只是一个文件系统。
指向原始笔记的链接
we realized that the big unlock was that it was just a file system.
—— Andrew Qu · [08:09]
Claude Code 并没有被给予一套非常死板规定的工具, 它某种程度上就是被放任自由, 去探索涌现行为。
指向原始笔记的链接
Claude Code was not giving a very prescriptive set of tools. It was sort of just letting it go wild and explore emergent behavior.
—— Andrew Qu · [08:34]
我写这篇文章的那一周, 它占了我们 Vercel.com 流量的 70%。
指向原始笔记的链接
And the week that I wrote this, it was responsible for 70% of our Vercel.com traffic.
—— Andrew Qu · [10:00]
于是我们真的在想: 如果我们为智能体构建一个 Next.js 会怎样?
指向原始笔记的链接
And so we actually thought, what if we built the Next.js for agents?
—— Andrew Qu · [12:04]
但我们发现, 真正让智能体好用的, 是它拥有大量非常具体的公司知识。
指向原始笔记的链接
But we found out that what really makes this agent good is it has a lot of very specific company knowledge.
—— Andrew Qu · [15:31]
如果你真的想获得最大的收益, 你应该真正尝试构建自己的智能体, 并尽可能多地加入公司特定的知识。
指向原始笔记的链接
if you really want to get the most juice out of a squeeze, you should really try to build your own agent and add in as much company-specific knowledge as you can.
—— Andrew Qu · [15:55]
② 出现在这些集
1 集
③ 他谈到的
点进去有真内容 —— 本页主要出口
智能体 · Vercel · Eve · Claude Code · Opus 4.5 · 沙箱 · 文件系统智能体 · 技能 · Snowflake · 语义层
