X：阿易 AI Notes

拿到Cursor赠送的$10000额度之后，我专门研究下这家公司， 看到Cursor CEO这个演讲，我突然意识到， 我们对AI编程的理解，从根上就错了， 当大多数人还在纠结哪个模型写代码更快更准的时候， Cursor已经直接进入了下一个时代， 工程师不再是写代码的人， 而是管理一整队AI同事的团队经理， 现在Cursor内部30%的合并PR， 都是由异步云代理自动创建的， 单周运行两千多个并发代理，生成三百万行代码， 消耗几十亿个token， 一个任务发出去， 系统会自动拆成规划，编码，测试，发PR四个角色， 每个代理独占一台远程机器，并行在云端运行， 人类只需要在最开始定义范围， 和最后做一次最终审核， 中间所有的脏活累活，AI全部自己搞定， 这就是多代理比单代理强的根本原因， Video

x.com/i/article/205838132931…

Beginner video: How to install & use Grok Build (made for non-technical SuperGrok and X Premium+ users) I got so many questions from friends, so I made this simple step-by-step guide. You’ll see exactly how to: • Install Grok Build in seconds with one command • Create real websites • Use Grok Imagine to auto-generate images & videos • Run multiple projects at once in different folders Grok even runs commands for you. No coding experience needed. Watch the full walkthrough 👇 Video

x.com/i/article/205838132931…

x.com/i/article/205838132931…

x.com/i/article/205868340950…

x.com/i/article/205838132931…

x.com/i/article/205838132931…

x.com/i/article/205838132931…

x.com/i/article/205838132931…

People often ask what my biggest tip is for getting the most out of Claude Code. These days my #1 tip is: use auto mode Auto mode means no more permission prompts. It is the key building block for multi-clauding: start a session, then while it runs, work on another session in parallel.

Damn，这个必须卧槽一下了，Karpathy 的 CLAUDE.md 只有 65 行， 居然能把 AI 编程准确率从 65% 拉到 94%， 以22 万星标登顶 GitHub 趋势榜，而且绝大多数开发者还没读过， 里面没有一行奇技淫巧，4 条规则全是同一个方向： → 先想清楚再写代码 陈述假设，不确定就问，杜绝猜测 → 从最简方案入手 只写能解决问题的最少代码，不加任何多余抽象 → 像手术一样精准修改 不碰与需求无关的代码，每行改动都对应明确要求 → 以目标驱动执行 写第一行代码前，把模糊指令转化为可验证的成功标准 65 行，4 条规则，每一条都在对抗开发者“先写再说”的本能， 本质上是把慢下来这件事变成硬规则， 趁别人还没保存，赶紧先存好 👇 Video

x.com/i/article/205730008435…

x.com/i/article/205730008435…

We are making our discount permanent! 🎉 Enjoy building with DeepSeek-V4-Pro and bring your innovative ideas to life! 🚀

Kay Zhu is the co-founder and CTO of @genspark_ai, the all-in-one AI workspace built on Claude. In a market moving this fast, where anyone can build, he thinks the team is what makes the difference: Video

x.com/i/article/205730008435…

karpathy's CLAUDE.md hit #1 on github trending. 220,000 stars. most devs still haven't read it. it's 65 lines. it took AI coding accuracy from 65% to 94%. the 4 rules inside: → think before coding state your assumptions. ask when unsure. never guess. → simplicity first write the minimum code that solves the problem. no abstractions nobody asked for. → surgical changes don't touch code unrelated to the request. every changed line must trace back to what was asked. → goal-driven execution turn vague instructions into verifiable success criteria before writing a single line. that's it. 65 lines. 4 rules. 94% accuracy. save this before everyone else does. Video

x.com/i/article/205766863457…

x.com/i/article/205730008435…

x.com/i/article/205730008435…