不读代码的五个真相：模型尚未达到完全自主
If you’re not reading the code, whether explicitly or through agentic inquiry, o…
If you’re not reading the code, whether explicitly or through agentic inquiry, one or more of these is true:
如果你没有阅读代码，无论是显式地还是通过代理式查询，那么以下情况至少有一种成立：
○ You’re a beginner ○ Software is throwaway ○ You’re prototyping ○ You have no users / revenue ○ You’re taking on debt & risk ○ Your problems are basic
○ 你是初学者 ○ 软件是一次性的 ○ 你在做原型 ○ 你没有用户/收入 ○ 你在承担债务和风险 ○ 你的问题很基础
And btw. All of this is fine. But the reality is that models are still not at the “full autonomy” stage yet.
顺便说一句，这一切都没问题。但现实是，模型还没有达到“完全自主”的阶段。
They make rookie mistakes, they go down bad architectural paths. I just had the best model in the world add a nonsensical 700ms delay to “settle” something and it told me “you’re right, I was cargo-culting” 🤨
它们会犯新手错误，会走上糟糕的架构路径。我刚刚让世界上最好的模型添加了一个无意义的700毫秒延迟来“稳定”某些东西，它告诉我“你说得对，我是在照搬教条”🤨
I am on the camp that this need will diminish more and more. Most code is indeed going to be assembly-like. But we also have the global internet and software infrastructure riding on these models and narrative, and we have to respect that.
我属于那种认为这种需求会越来越少的阵营。大多数代码确实会变得像汇编一样。但我们也依赖这些模型和叙事来支撑全球互联网和软件基础设施，我们必须尊重这一点。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力