The Collective Intelligence Leap: Deep Diving into Group-Evolving Agents (GEA)

The current trajectory of artificial intelligence points toward a singular, ambitious goal: open-ended self-improvement. The idea is to… Continue read...

I’ve Reviewed 1,000 Pull Requests. These 7 Patterns Separate Junior From Senior.

It’s not code quality. It’s how they handle uncertainty. Continue reading on Dev Genius »

The End of Code? Why AI Won’t Replace Developers ,But Will Transform Everything Else

The fear is real. The reality is more interesting. Continue reading on Medium »

The Evolution of AI Prompting: How 4 Years of Research Inspired My New Claude Code Skill

We use Large Language Models every day to write code across different languages and frameworks. But how does an AI actually reason about our code? I r...

Pair Programming Was Never About Two Keyboards. It Was About Two Minds.

AI didn’t kill pair programming. It quietly replaced the navigator and we barely noticed. Continue reading on Medium »

Voice is the new CLI: Why 2026 is the year of Agentic Dictation

The bottleneck in AI isn’t the model. It’s the input. Continue reading on Medium »

The Loom Does Not Care Who Owns It

There was a man called Xosé who worked in a textile factory outside A Corunha for thirty-one years. He started at seventeen, sweeping floors, and by t...

Understanding LSTMs – Part 2: The Long-Term and Short-Term Memory Paths

In the previous article we just began with the concept of LSTMS and its diagrams. In this article we will slowly start understanding the LSTM structur...

How I’d Learn ML in 2026 (If I Could Start Over)

All you need to learn ML in 2026 is a laptop and a list of the steps you need to take. Continue reading on Towards AI »

I Didn’t Wait Until I Was Ready. I Just Built It.

On the difference between writing code and building something production-ready. Continue reading on Medium »

Cursor Isn’t a ChatGPT Wrapper. It’s an Intelligent System.

Most people think Cursor is just a ChatGPT wrapper. That misunderstanding alone tells you how early we still are in the AI era. Continue reading on Me...

When AI Writes the Code, Who's Accountable When It Breaks?

Last quarter, a team I know shipped a bug in production. Customer data was briefly exposed to wrong users — not stolen, but visible. The root cause wa...

9 Python Best Practices I Don’t Follow Anymore

Context matters Continue reading on Python in Plain English »

HNSW at Scale: Why Adding More Documents to Your Database Breaks RAG

We Added More Documents. Answers Got Worse. Continue reading on Towards AI »

[MM’s] Boot Notes — SOAP in 2026

Why Contract-First Design Is Becoming Relevant Again — and SOAP Already Solved It. Continue reading on Medium »

Build an LLM-Powered Weather App with Go and Genkit Tool Calling

Give your LLM access to live APIs with Genkit’s tool calling support in Go Continue reading on Medium »

Kotlin Classes: A Comprehensive Guide

Introduction Classes are one of the fundamental building blocks of object-oriented programming in Kotlin. They allow you to encapsulate data and behav...

From Documents to Answers: How RAG Works

The main steps to build a RAG pipeline are divided into two major processes: RAG Indexing RAG Query RAG INDEXING The indexing phase converts raw docum...

Building applications with google AI studio

Provably Fair Gambling for AI Agents — How It Works

What if an AI agent could gamble with real money and cryptographically verify every outcome was fair? Why Agents Gamble It sounds strange, but there a...