Boris Cherny
① 他说过的话
18 条
最大的原因是模型改进得太快了，我们觉得真的没有其他形态能跟得上它。
指向原始笔记的链接
The biggest reason was the model is improving so quickly, we felt that there wasn’t really another form factor that could keep up with it.
—— Boris Cherny · [11:06]
而且如果你看那条指数曲线，那个时间点由 Claude 编写的代码百分比，如果你只是沿着线画过去，很明显我们在年底就会超过 100%，即使这完全不符合直觉。
指向原始笔记的链接
If you look at the exponential, the percent of code that was written by Claude at that point, if you just trace the line, it’s pretty obvious we’re going to cross 100% by the end of the year, even if it just does not match intuition at all.
—— Boris Cherny · [14:40]
所以，我认为，在这个节点，可以说编码几乎已经解决了。
指向原始笔记的链接
I think, at this point, it’s safe to say that coding is virtually solved.
—— Boris Cherny · [18:19]
至少，对于我做的那些编程类型来说，这只是一个已解决的问题，因为 Claude 能做到。
指向原始笔记的链接
At least, for the kinds of programming that I do, it’s just a solved problem, because Claude can do it.
—— Boris Cherny · [18:23]
但是每个工程师的生产力在拉取请求方面增加了 200%。
指向原始笔记的链接
But productivity per engineer has increased 200% in terms of pull requests.
—— Boris Cherny · [21:25]
当你在所有事情上稍微投入不足时，会发生一件有趣的事情，因为那样人们被迫去 Claude 化。
指向原始笔记的链接
There’s an interesting thing that happens also when you under-fund everything a little bit, because then people are forced to Claude-ify.
—— Boris Cherny · [24:21]
我的看法是，对于今天正在使用 Claude Code，正在使用智能体写代码的人来说，你仍然必须理解底下那层，但是，是的，在一两年后，这就不重要了。
指向原始笔记的链接
My take is I think for people that are using Claude Code, that are using agents to code today, you still have to understand the layer under, but, yeah, in a year or two, it’s not going to matter.
—— Boris Cherny · [32:27]
然后，在某个时候，古腾堡和印刷机出现了，有一个疯狂的统计数据，在印刷机建成后的 50 年里，创造的印刷材料比之前的 1000 年还要多。
指向原始笔记的链接
And, at some point, Gutenberg and the printing press came along, and there was this crazy stat that in the 50 years after the printing press was built, there was more printed material created than in the thousand years before.
—— Boris Cherny · [33:22]
我们说，“产品就是模型。我们想要把它暴露出来。我们想要在它周围搭建最小化的脚手架。给它最小的工具集。“
指向原始笔记的链接
We said, “The product is the model. We want to expose it. We want to put the minimal scaffolding around it. Give it the minimal set of tools.”
—— Boris Cherny · [51:29]
但实际上，如果你只给模型工具，给它一个目标，然后让它自己弄明白，几乎总是能得到更好的结果。
指向原始笔记的链接
But actually almost always you get better results if you just give the model tools, you give it a goal, and you let it figure it out.
—— Boris Cherny · [64:06]
我们押注于为六个月后的模型构建。而不是为今天的模型。
指向原始笔记的链接
We bet on building for the model six months from now. Not for the model of today.
—— Boris Cherny · [65:56]
通常，如果你使用最强大的模型，实际上反而更便宜，且消耗更少 token，因为它可以只用更少的纠错、更少的指导等就把同样的事情做得更快。
指向原始笔记的链接
Often, it’s actually cheaper and less token-intensive if you use the most capable model, because it can just do the same thing much faster with less correction, less hand holding, and so on.
—— Boris Cherny · [69:39]
字面意义上，就是在提示词注入发生时，观察模型大脑中亮起的神经元。
指向原始笔记的链接
where it’s literally, we’re looking at neurons in the model’s brain that light up when prompt injection happens.
—— Boris Cherny · [03:00]
只有当你看到它反复在同一件事上绊倒时，你才应该把它加回去。
指向原始笔记的链接
And only when you see it repeatedly stumble on the same thing, that’s when you add it back.
—— Boris Cherny · [08:36]
通常，我们只是让 eval 饱和，然后我们必须把它扔掉，我们必须想出一个新的 eval。
指向原始笔记的链接
Very often, we just saturate the eval, and then we have to throw it away, and we have to come up with a new eval.
—— Boris Cherny · [10:36]
它运行了11天。它重写了整个代码库。
指向原始笔记的链接
And it ran for 11 days. And it rewrote the entire code base.
—— Boris Cherny · [18:01]
验证，我认为，可能是人们做不对的单一最重要的事情，大体上。
指向原始笔记的链接
And the verification, I think, is probably the single most important thing that people do not get right, largely.
—— Boris Cherny · [20:51]
忘掉你在课堂上学到的关于计算机科学理论的所有东西。
指向原始笔记的链接
forget everything that you learned about computer science theory in class.
—— Boris Cherny · [32:11]
② 出现在这些集
2 集
③ 他谈到的
点进去有真内容 —— 本页主要出口
智能体 · 沙箱 · Lenny · Cloud Code · Claude Code · Opus 5 · Anthropic · 提示词注入 · Cowork · 系统提示词