DeepSeek Harness Team Interview Prep: Model + Harness = Agent
I recently read an article about preparing for the DeepSeek Harness team interview that explains the core concepts of Agent engineering in a way “even...
写作热力图
加载中...
加载中...
少
多
2026
DeepSeek Harness 团队面试准备：Model + Harness = Agent
最近读到一篇关于 DeepSeek Harness 团队面试准备的文章，用「五岁小朋友都能听懂」的方式把 Agent 工程里的核心概念讲得很清楚。我整理成笔记，方便后续复习，也分享给正在准备相关岗位面试的同学。 原文链接：DeepSeek Harness 团队面试准备 核心等式Model + Ha...
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...
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
DeepSeek Harness Team Interview Prep: Model + Harness = Agent
I recently read an article about preparing for the DeepSeek Harness team interview that explains the core concepts of Agent engineering in a way “even...
DeepSeek Harness Team Interview Prep: Model + Harness = Agent
I recently read an article about preparing for the DeepSeek Harness team interview that explains the core concepts of Agent engineering in a way “even...
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