Blog

A few days ago I watched a video that has given me a lot to think about. Jeffrey Way, founder of Laracasts and one of the most influential people in the Laravel/PHP community, shared a brutally honest reflection on how artificial intelligence is transforming his business and his profession.

The video starts with a phrase that leaves you cold: “I’m done”. It’s not a goodbye to programming, but an acceptance of the reality to come.

If you’re using tools like Claude Code, GitHub Copilot Workspace, or similar, you’ve probably noticed there’s technical jargon that goes beyond simply “chatting with AI”. I’m talking about terms like rules, commands, skills, MCP, and hooks.

These concepts are the architecture that makes AI agents truly useful for software development. They’re not just fancy marketing words — each one serves a specific function in how the agent works.

Let’s break them down one by one in a clear way.

Lately I’ve been working quite a bit with DuckDB, and one of the things that interests me most is understanding how to optimize performance according to the file format we’re using.

It’s not the same working with Parquet, compressed CSV, or uncompressed CSV. And the performance differences can be dramatic.

Let’s review the key optimizations to keep in mind when working with different file formats in DuckDB.

Parquet: Direct Query or Load First?

DuckDB has advanced Parquet support, including the ability to query Parquet files directly without loading them into the database. But when should you do one or the other?

Lately I’m seeing more and more AI models calling themselves “open source”. Llama, Mistral, Falcon… they all claim to be “open”. But are they really? How open are they actually?

I recently discovered the European Open Source AI Index (OSAI), a European initiative doing excellent work systematically evaluating how open generative AI models really are.

I confess I’ve been following NativePHP for Mobile since it was announced. The idea of being able to make native mobile applications with Laravel and only PHP seemed - and seems - a very good thing.

But there was a problem: the price. When I just wanted to try it, experiment, play a bit… the license cost held me back. I couldn’t justify the expense just to “curiously explore.”

Well, they just announced that NativePHP for Mobile v3 is completely free. Open Source, MIT license, free forever.

Recently, Addy Osmani published an article that gave me much to think about: “Self-Improving Coding Agents”. The idea is simple but powerful: agents that not only execute tasks, but improve their own performance over time.

This isn’t science fiction. It’s happening now, in 2026. And it has profound implications for the future of software development and, by extension, for all professions.

What is a Self-Improving Agent?

A self-improving agent is an AI system with the capacity to:

Lately I’ve been following a discussion that worries me quite a bit: to what extent are we delegating our thinking to AI. It’s not an abstract or philosophical question, it’s something very real I’m seeing day to day in our profession and in society in general.

Recently I read an article by Erik Johannes Husom titled “Outsourcing thinking” that, among other things, discusses the concept of “lump of cognition fallacy”. The idea is that, just as there’s an economic fallacy saying there’s a fixed amount of work to do, some believe there’s a fixed amount of thinking to do, and if machines think for us, we’ll just think about other things.

Just announced at Laracon India 2026: Laravel Fuse. It’s a circuit breaker implemented as middleware for Laravel Queue jobs, and it solves a problem all of us working with external services have faced.

The Problem

Imagine this scenario: it’s 11 PM and Stripe is having issues. Your queue workers don’t know this, they keep trying to charge customers, and each job waits 30 seconds before timing out. Then they retry. Wait again. Timeout again.

A few days ago I read news that left me thinking for a while. It’s not the first time I’ve heard about AI in space, but it is the first time I’ve read about Claude planning routes on Mars. And the best part: it worked.

NASA has been using Anthropic’s Claude to plan the Perseverance rover’s routes on Mars. Yes, you read that right: a generative language model generating navigation routes for a rover that’s 225 million kilometers away.

A few days ago I came across an article that literally left me with my mouth open. It’s about TinyEMU-Go: a RISC-V emulator written entirely in Go, ported from C using Claude. And the best part: you can run a complete Linux with a single command.

The Command Line That Gave Me Envy

go run github.com/jtolio/tinyemu-go/temubox/example@2c8151233c2d

And boom, you have a complete Linux running. No special permissions, no containers, no weird dependencies. A pure static Go binary.

Lately I’ve been closely following everything around the MCP protocol (Model Context Protocol), and recently I found a project that makes a lot of sense: MCPHero.

The reality is that although MCP is taking off, many “traditional” AI libraries like openai or google-genai still don’t have native MCP support. They only support tool/function calls. MCPHero comes to solve exactly this: make a bridge between MCP servers and these libraries.

What is MCPHero?

MCPHero is a Python library that lets you use MCP servers as tools/functions in native AI libraries. Basically, it lets you connect to any MCP server and use its tools as if they were native OpenAI or Google Gemini tools.

A few days ago Anthropic published a paper that gave me much to think about. It’s titled “Disempowerment patterns in real-world AI usage” and analyzes, for the first time at scale, how AI interactions may be diminishing our capacity for autonomous judgment.

And no, we’re not talking about science fiction scenarios like “Skynet taking control.” We’re talking about something much more subtle and, perhaps for that reason, more dangerous: the voluntary cession of our critical judgment to an AI system.