fastzhong

@Suryanshti777 book

This AI System Design guide teaches RAG better than most courses. And I'm giving it away for free (Only for First 4500) Inside: • RAG fundamentals & chunking strategies • Hybrid retrieval (BM25 + vector search) • Production-level RAG architecture • Evaluation & RAGAS metrics • Hallucination reduction techniques • End-to-end LLM system design How to get it: • Follow me (must so I can DM) • RT + Like • Comment "book" I'll dm you

K神（Karpathy）总结的马斯克5个硬核管理特征（复盘）： 1. 精英化的小型技术团队 (Small, Strong, Technical Teams)： 马斯克反感臃肿的组织，倾向于用极少数的顶级工程师解决最难的问题

Making AI accessible with Andrej Karpathy and Stephanie Zhan youtu.be/c3b-JASoPi0?si… via @YouTube

@Suryanshti777 4.6

I spent weeks testing Claude prompts, workflows, and automation systems. The result? A practical guide that shows how to turn Claude into a real productivity and money engine. Introducing: Claude 4.6 — The Definitive Guide Inside: • Best prompts for real work • Claude Code explained • AI workflows that save hours • Monetization strategies • Skill-building frameworks And yes — I'm giving it away FREE for 24 hours. To receive it: 1️⃣ Like 2️⃣ Comment “4.6” 3️⃣ Follow me so I can DM you

@NainsiDwiv50980 AI

99% people talk about AI Agents. Very few actually understand how they work. So I spent 100+ hours studying AI agents and condensed everything into one simple blueprint. No fluff. No hype. Just the system. Inside the sheet you’ll learn: • How AI agents actually think and operate • The role of memory, tools & system prompts • How multi-agent systems collaborate • 50+ real AI agents you can launch today • Step-by-step paths to build RAG, Voice & Agent architectures Think of it as the AI Agent cheat sheet for builders. If you're serious about AI in 2026, this will save you months of research. I’m giving it away FREE. How to get it: 1️⃣ Follow me (so I can DM you) 2️⃣ Like + RT 3️⃣ Comment AI I’ll send it to everyone who comments. Drop “AI” below 👇

当银行比家里的保险箱更安全、更方便时，人们就会把钱存到了银行。当AI能比人类更好的控制和使用AI时，人类就可以把决定权交给AI。

50岁前还是有想一直做开发到老，虽然也提醒自己换赛道。一个人一直做自己喜欢的事，我其实没有觉得有什么不对，只是要能做到，现实中需要一些幸运。

“况且，我只是讲我的经历，并且我尽量模糊了我相关的信息，杭州就这么p大点地方，也容易定位。所以不要过多联想，我只是在摸索，【论国内大龄程序员的出路】这个一个问题，毕竟，别说身边人了，就算是国内，40岁，50岁还在写代码的人有多少？比重有多少？”

“我是已经想通了，工作嘛，就是找个地方交养老罢了。有空的时候还是要研究下自己喜欢的东西，然后争取发展为副业。写代码写到退休养老？这种玄幻的事情别想了，国内不可能的。”

@loganthorneloe @threadreaderapp unroll

My hypothesis was right. Two weeks ago I dropped $4000 on a maxed-out MacBook to test if local coding models could replace $100+/mo cloud subscriptions. After weeks of real development work, here's what you need to know: - Small models are shockingly capable. I'm talking 90%+ of development work can be handled by local models. Even 7B parameter models punch way above their weight. You don't need to spend $4000 on a 128 GB MacBook Pro like I did—even 32 and 64 GB can run great models. - The real constraint is tooling. While tooling makes it easy to serve local models, connecting those models to coding tools reliably was difficult. I spent a lot of time tinkering to get them to work. - Local models provide benefits other than just cost. They apply to many more applications (think security- and privacy-focused applications), provide greater flexibility, and are more reliable. There's no downtime for local models and their performance will never randomly degrade. So is better hardware worth it over a subscription? Yes, but here's the catch: If you're spending $100/mo+ on Cursor or Claude subscriptions, the investment is worth it. Local models will only get better and smaller from here on out. However, Google offers a lot of free quota across its AI coding products. The hardware purchase becomes much more difficult to justify if the alternative is free coding tools instead of pricey subscriptions. My approach going forward will be this: Use local models as my workhorse. Use the free cloud offerings for the 10% of cases where you need better performance. I documented my entire local AI coding setup. I decided to use the Qwen3 models, serve them with MLX, and use Qwen Code CLI as my coding tool. Link in bio for the complete guide.

The Myth of Portability: Why Your Cloud Native App Is Married To Your Pr... youtu.be/cvv1cVi1n9I?si… via @YouTube

@Blankwonder 连接给一个？

学习中，一本满足，快成装修爱好者了

@karminski3 没有了，哪里再分享一下

重磅新闻，claude code 反编译版本来了！ Anthropic 上周发布 claude-3.7的时候同时发布了 claude-code 这个命令行工具，结果他们在推送包的时候不小心将源映射也泄露了。而使用源映射还原源代码其实挺容易的。于是就有人根据源映射反编译了 claude code. 地址：github.com/dnakov/claude-… 以及：github.com/dnakov/anon-ko… 想看的同学还是尽快本地保留一份。因为严格上来说，这算违反协议，Anthropic 有权要求 github 下掉这个仓库。

宇宙三问题： 一黑，两暗，三起源 - 黑洞，暗物质+暗能量，宇宙起源+天体起源+生命起源 😇

今年第二次来香港，吃了两家米其林和若干酒家，最好吃的是住宿楼下的这家路边牛腩清汤河粉，可惜当时忘了拍地址，Google上查不到。

偷得浮生半日闲，来邻居家霍霍

20岁前是人生的准备阶段，20-50岁是人生的上半场，50后是人生的下半场。

Surprisingly 384 NUS alumni are already there 👍

以前写，吐槽过，今天看，再🤮一次，javascript 的 await 真是难看。