karpathy-guidelines：让 AI 写代码更靠谱的四个原则
“LLM 写代码最大的敌人，不是不会写，而是写太多、想太少、改太乱。” —— 这是 Andrej Karpathy 在观察了大量 AI 辅助编程案例后的总结。 最近我在整理自己的 AI 开发工具链时，在 GitHub 上发现了一个很有意思的项目：andrej-karpathy-skills。它把...
写作热力图
加载中...
加载中...
少
多
2026
karpathy-guidelines: Four Principles That Make AI Write More Reliable Code
“The biggest enemy of an LLM writing code isn’t that it can’t write, but that it writes too much, thinks too little, and changes things too messily.”...
2026
karpathy-guidelines: Four Principles That Make AI Write More Reliable Code
“The biggest enemy of an LLM writing code isn’t that it can’t write, but that it writes too much, thinks too little, and changes things too messily.”...
karpathy-guidelines: Four Principles That Make AI Write More Reliable Code
“The biggest enemy of an LLM writing code isn’t that it can’t write, but that it writes too much, thinks too little, and changes things too messily.”...
1