Abdush Shakoor

I’m just curious, always @

[el.cine @EHuanglu]

codex + blender is insane

[Dan Kornas @DanKornas]

awesome-rag just turned RAG research sprawl into a single reading map for LLM builders.

The painful part of RAG is not only retrieval.

It is deciding which papers, codebases, talks, and tools are worth opening first.

The repo organizes the map instead of adding another framework.

The useful part:
> survey + general RAG papers
> code/blog/Hugging Face links where available
> lectures, tutorials, and workshops
> tools like LangChain, LlamaIndex, Verba, NEUM, Kiln, Unstructured, CocoIndex

Public repo, licensed CC0 1.0 Universal.

If you were learning RAG today, would you start from surveys or implementation code?

Link in the reply 👇

[Bilgin Ibryam @bibryam]

How to Setup a Local Coding Agent on macOS
https://t.co/3KVWHDx74w

[Jaydeep @_jaydeepkarale]

A web-based System Design Simulator, where you drag & drop architecture components and actually simulate traffic, failures, latency, and scaling in real time

Best way to learn concepts.

Link in next post post

[Ihtesham Ali @ihtesham2005]

A Japanese programmer looked at every existing programming language in 1993, decided none of them made him happy, and spent two years building his own the language he built became the foundation GitHub, Shopify, Airbnb, and Coinbase were all built on.

His name is Yukihiro Matsumoto.

Everyone in the programming world calls him Matz. He was born in 1965, studied information science at the University of Tsukuba, and graduated in 1990 with a head full of ideas about what programming languages could be and a quiet frustration with what they actually were.

He knew Perl. He did not like it. He said it had the smell of a toy language. He knew Python. He did not like it either, because he felt its object-oriented features were add-ons bolted onto a language that was not designed around them from the start. He wanted something that was genuinely, completely object-oriented, easy to use, and built for the person writing the code rather than the machine running it.

He looked for that language. He could not find it.

So on February 24, 1993, he opened a chat window with his colleague Keiju Ishitsuka and typed: "Let us decide the codename now."

They wanted to name it after a gemstone, inspired by Perl. Ishitsuka suggested Coral. Matsumoto suggested Ruby. Ruby was shorter by one letter. Ruby won.

He spent the next two years building it alone, working through the architecture piece by piece. The object system. The string class. The IO streams. He later said he talked through specific features while speaking to his baby daughter, using her as a sounding board the way programmers use rubber ducks. In August 1993, he finally wrote the line of code that produced "Hello, world." on the screen.

The first public version, Ruby 0.95, was released to Japanese domestic newsgroups on December 21, 1995. No press release. No launch event. Just a quiet post to a mailing list.

The design principle underneath everything was the one nobody else had ever made primary. Matsumoto called it programmer happiness. He believed programming languages should be built for the joy and productivity of the person writing the code, not optimized purely for machine efficiency. Every decision in Ruby's design ran through that filter. If it made the programmer's life harder, it was wrong.

That philosophy attracted a small but devoted following in Japan through the late 1990s. Then in 2003, a Danish programmer named David Heinemeier Hansson discovered Ruby and used it to build an internal project management tool for his company. He called the tool Basecamp. He extracted the framework underneath it and released it publicly in 2004.

He called it Ruby on Rails.

Within a year of that release, the framework had changed how web applications were built. Rails introduced the principle of convention over configuration, meaning developers could make decisions about structure quickly because the framework had already made sensible defaults. What used to take weeks of setup took days. What used to take days took hours.

Shopify started on Rails in 2005. GitHub built on Rails a couple of years later. Airbnb, Twitch, Coinbase, SoundCloud, and Zendesk all followed. The first generation of consumer internet companies that defined how people think about software products were largely built by small teams moving fast on a framework that traced directly back to one Japanese programmer who was dissatisfied with his tools in 1993.

Shopify now processes over $200 billion in annual commerce volume. It still runs on Rails. GitHub became the largest code hosting platform on earth and was acquired by Microsoft for $7.5 billion in 2018. It started on Rails.

Matsumoto has said many times that he created Ruby for selfish reasons. He was so underwhelmed by every available option that he built something that would make himself happy. The programmer happiness he was chasing was his own.

The community that grew around Ruby adopted a motto that says everything about who he is. Matz is nice and so we are nice. They abbreviated it MINASWAN. It spread because it was true. He answered emails from strangers. He engaged with the community with patience. He treated the language as a gift, not a product.

He is still the chief designer of Ruby today. The language is 31 years old. It is still being improved.

The last stable release was Ruby 4.0.4, shipped on May 11, 2026.

One programmer, unhappy with his tools, built something better in the evenings in 1993. The companies you use to buy things, to store code, to book travel, and to watch streams were built on top of what he made.

He just wanted to be happy while he worked.

Did you know Ruby was behind the tools you use every day?

[Tom Dörr @tom_doerr]

Comprehensive guide to self hosting software and hardware

https://t.co/yC4OGlQC7b

[Sumanth @Sumanth_077]

Hands on AI Engineering!

I open-sourced a collection of 50+ hands-on AI engineering tutorials.

It features step-by-step projects and tutorials on:

• AI Agents and Multi-agents
• RAG (Agentic, Vision, and Local)
• MCP AI Agents
• OCR Apps
• Voice AI Agents
• & so much more

100% free and open source. 1k+ Github stars

I've shared the link in the comments!

[Harshavardhan Reddy Vogulam @lazymlguy]

The difference between a $100k ML engineer and a $300k ML engineer is rarely model knowledge.

It’s system design.

These 3 books will teach you how real AI products are built:

1. Designing Machine Learning Systems
https://t.co/Sy5paO08o5
2. AI Engineering
https://t.co/rmbplL5TNH
3. Machine Learning System Design Interview
https://t.co/kEnIR5z7e5

If you’ve read one of these, which had the biggest impact?

[Praveen Kumar Verma @Alacritic_Super]

MIT made its entire AI & ML library 100% FREE to access.

These 12 books are the best place to start 👇

↳ 𝗙𝗼𝘂𝗻𝗱���𝘁𝗶𝗼𝗻𝘀

1. Foundations of Machine Learning
https://t.co/G28Kc0JlkA
The mathematical backbone of ML - algorithms, theory, and how models actually learn.

2. Understanding Deep Learning
https://t.co/jFsC5Qbxkn
Neural networks explained visually and intuitively, from basics to modern architectures.

3. Deep Learning
https://t.co/eG41C2Ywpv
The definitive deep learning reference, written by the researchers who shaped the field.

4. Introduction to Machine Learning Systems
https://t.co/TFMVq2kJik
How to design and build ML systems that work in production, not just in notebooks.

5. Algorithms for Optimization
https://t.co/QXJKY3S8EV
The math behind how models improve - gradient methods, search, and decision-making.

↳ 𝗥𝗲𝗶𝗻𝗳𝗼𝗿𝗰𝗲𝗺𝗲𝗻𝘁 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴

6. Reinforcement Learning: An Introduction
https://t.co/7lSKfdfPlI
The classic RL textbook - how agents learn to make decisions through trial and reward.

7. Distributional Reinforcement Learning
https://t.co/rIhR4IseyG
Goes beyond average rewards to model the full distribution of outcomes.

8. Multi-Agent Reinforcement Learning
https://t.co/gYObFIZoQz
How multiple AI agents learn, compete, and cooperate in shared environments.

↳ 𝗣𝗿𝗼𝗯𝗮𝗯𝗶𝗹𝗶𝘀𝘁𝗶𝗰 𝗠𝗟

9. Probabilistic Machine Learning: An Introduction
https://t.co/1OGhPhHwFO
ML through the lens of probability - uncertainty, inference, and Bayesian thinking.

10. Probabilistic Machine Learning: Advanced Topics
https://t.co/xizTNW6afo
Deep dives into probabilistic models, approximate inference, and generative methods.

↳ 𝗥𝗲𝘀𝗽𝗼𝗻𝘀𝗶𝗯𝗹𝗲 & 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗔𝗜

11. Agents in the Long Game of AI
https://t.co/GDcUVd70qV
How to build AI agents that are trustworthy, hybrid, and designed for long-term reliability.

12. Fairness and Machine Learning
https://t.co/erAtyZs9Hi
Where ML meets society - bias, discrimination, and how to build more equitable systems.

If you're serious about AI/ML, these books are a great starting point to build a solid foundation.

[Neo Kim @systemdesignone]

10 Books that will make you a 10x AI engineer:

1 Building LLMs for Production
2 AI Engineering
3 Designing Machine Learning Systems
4 Build a Large Language Model
5 Designing Data-Intensive Applications
6 LLM Engineer's Handbook
7 Deep Learning
8 Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow
9 Prompt Engineering for LLMs
10 Introduction to Statistical Learning

What else should make this list?

[Neo Kim @systemdesignone]

If you want to get ahead of 99% of software engineers, then read these 12 books:

1 Designing Data-Intensive Applications
2 Clean Code
3 The Pragmatic Programmer
4 The Mythical Man-Month
5 Introduction to Algorithms
6 Code Complete
7 The C Programming Language
8 Refactoring
9 The Art of Computer Programming
10 Structure and Interpretation of Computer Programs
11 Peopleware
12 Design Patterns

What else should make this list?

[BookNote @BookNoteApp]

10 books that could replace a university degree:

1) How to Solve It by George Pólya

[Matt Pocock @mattpocockuk]

Steps to become a senior programmer:

1. Install my /teach skill

npx skills add mattpocock/skills --skill teach

2. Create a new working directory on your laptop

mkdir junior-to-senior
cd junior-to-senior

3. Kick off your coding agent in the directory

claude

4. Copy this prompt

/teach me how to be a great strategic programmer. My opinion is that AI is eating 'tactical, on-the-ground' programming. The day-to-day work of a developer involves not only coding, but also planning, QA, codebase design, and much more. I'm interested in learning the strategic skills - that, in a previous era, would take me from junior to senior - but in this era are table stakes.

5. Paste it into the coding agent

Below is an example of what the first output will look like. I used Opus 4.8, medium effort.

6. Continue working with the agent until you're a senior

[John Carmack @ID_AA_Carmack]

I admire Fabrice Bellard. He is almost certainly a better overall programmer than I am.

[Fatih Arslan @fatih]

Control Theory meets Kubernetes. One of the images from my upcoming blog post about deep dive into controllers and closed feedback loops in Kubernetes.

[Miguel Ángel Durán @midudev]

¿Cómo liberar gigas de disco si eres programador?
Limpia todos los node_modules que no usas.

Ejecuta el comando: npx npkill

Te muestra las carpetas node_modules y sus tamaños.
Dale [Espacio] para eliminar las que ya no uses ↓

[H @hmmmmmm1458]

난 게임을 즐겨하지 않는데 이런건 진짜 유익함

만원으로 데이터 센터의 복잡한 구조와 컴퓨터 인프라를 이해하는 스팀게임 : Data Center

빈 방에서 시작해서
랙 구매 → 서버 장착 → 모든 케이블을 직접 손으로 하나하나 연결해야함

실제 데이터 센터처럼 고객 트래픽을 처리하는 시뮬레이션 게임

출시 48시간 만에 180개가 넘는 리뷰가 달렸고, 플레이어들은 “최근 본 시뮬레이션 게임 중 가장 몰입감 있다”, “컴퓨팅 인프라를 이해하는 데 최고”라는 평가를 하고 있습니다.

[Raul Junco @RaulJuncoV]

A backend engineer asked me why I recommend Fundamentals of Data Engineering for backend folks.

Because most backend engineers accidentally become data engineers the moment their API hits production.

Backend = owns writes.
Data Engineering = owns reads.
But both eat the same consequences when the data sucks.

If you learn Data Engineering fundamentals, you level up faster because you stop treating data as “someone else’s problem.”

You get better at:

- Designing schemas that won’t break downstream
- Shipping clean, traceable events (no dual-write disasters)
- Thinking in batch vs. streaming trade-offs
- Debugging data issues faster than “blame analytics”
- Building APIs that scale with actual usage patterns

Backend without data fundamentals = “the feature works”
Backend with data fundamentals = “the business trusts what you build”

The short answer:
Most backend engineers only understand half the system.

This book helps you finally see the whole thing.

[Shalini Goyal @goyalshaliniuk]

5 GitHub repos that will automate your daily life.

All free. All open source. All doing work you currently do manually every single day.

[Bhavya @Bhavyaztwt]

Things every performative senior software Engineer needs