John Lindquist
① 他说过的话
8 条
我想到我在这方面花的所有时间，还有我做过的几百个 demo，我想我一共只花了 73 美分。
指向原始笔记的链接
I think of all the time I’ve spent on this and the hundreds of demos I made, I think I’ve spent 73 cents on it.
—— John Lindquist · [02:46]
这里的力量在于这是人类在与机器对话：你已经把函数、API 等一切都设置好了，但你想用非结构化的数据与它们沟通。
指向原始笔记的链接
And the power there is it’s humans talking to machines, and they’re the scenarios where you have functions and APIs and everything set up, but I want to communicate with them using unstructured data.
—— John Lindquist · [05:49]
因为你注意到我整段讲话期间，从未停顿，从未按回车。它能够分类判断：这是一个我有足够信息采取行动的时刻吗？
指向原始笔记的链接
Because you notice that entire time I was talking, I never paused, I never hit enter. It was able to classify, is this a moment where I have enough information to take action?
—— John Lindquist · [07:54]
这里有一些基准测试，Jev 在平均走法上快了 10 倍，便宜了 4 倍。
指向原始笔记的链接
it has some benchmarks over here that Jev was 10 times faster in the average move and it was four times cheaper.
—— John Lindquist · [21:41]
但一旦动作确定下来，你有了那个有限的范围，那就是一个决策模型能真正大放异彩的地方——至少从我到目前为止的经历来看是这样。
指向原始笔记的链接
But once the actions are set and you have that limited scope, that’s where A decision model can really excel, at least from what I’ve experienced so far.
—— John Lindquist · [24:19]
说实话，它感觉更像编程——当看到出问题时，我感觉自己掌控力强得多，因为我知道它所有的选项，我知道我想要什么。
指向原始笔记的链接
It feels much more like programming, to be honest, where I feel much more in control when I see something goes wrong because I know all of its options and I know what I want.
—— John Lindquist · [32:51]
因为它又快又免费，别担心，就再加一层；然后随着时间推移、随着越来越多数据强化了从一步到下一步所需的确切流程，你可以把那些层压缩成单层。
指向原始笔记的链接
because it’s fast and free, don’t worry about adding just another layer and then Over time, you could compress those down into a single layer as you get more and more data that reinforces what the exact flows are that you need to go from from step to step.
—— John Lindquist · [38:36]
我认为在我们与工具的关系上，这是一个非常重大的转折点——我们不再思考以前思考的所有事情，除了给智能体买更多硬盘来用。
指向原始笔记的链接
And I think it’s a really big turning point in our relationships with our tools as we stop thinking about everything we thought about before other than buying more hard disks for agents to use.
—— John Lindquist · [43:21]
② 出现在这些集
1 集
- 《又快又免费的 Jev：让 AI 变成「最聪明的函数」》 — 作为联合主持
③ 他谈到的
点进去有真内容 —— 本页主要出口
Clara Vo · Jev · TypeSafe AI · LLM · 函数调用 · 智能体 · 置信度分数 · 路由器 · 实时 · 浏览器使用