I write about software in general, and now I want to talk more about hardware and IoT.

Here will be centralized all the old and current posts and thoughts, with tips and some solutions that I have implemented throughout my career.

The Anatomy of a Good RFC

Every RFC that works has six essential pieces. If you know how to assemble them for humans, you already know how to assemble them for AI agents.

The RFC Nobody Read and the Prompt Nobody Wrote

The same discipline that makes an RFC work for human engineers is what makes a prompt work for AI agents. Most developers already have this skill - they just haven't realized it yet.

Tick-Tock: The Strategy to Never Break Your Software

How the Tick-Tock strategy I learned while working at Woovi ensures you can evolve your software without breaking anything. Applied to database changes, feature evolution, and APIs.

The 50-Token Rule That Proves We've Been Wasting GPU Memory

Researchers discovered that shuffling words 50 tokens ago doesn't change predictions at all. This insight led to architectures that are 23% leaner and 30% faster. Here's how treating distant text like blurry peripheral vision changes everything.

The Tiny AI That Humiliated a Supercomputer

MIT researchers built an AI model that beat Google's 250 GPU-year monster while emitting less CO2 than your morning coffee. Here's the story of how brains beat brute force.

ClawdBot Is Amazing. And You Should Be Careful Using It.

I spent the week playing with ClawdBot and I get the hype. It genuinely feels like having Jarvis. But we need to talk about the risks of running an autonomous agent with full access to your machine.