Kartones Blog

On AI, building things, and sharing them

Kartones — Sat, 17 Oct 2026 11:00:00 +0200

I've been less active online lately, including writing less, due to a combination of things. But I felt this could be one of those brain-dump posts where I just loosely link some thoughts as I write them.

At the time of writing this post, last weekend we co-located the final …

Learning to draw pixel art

Kartones — Wed, 26 Aug 2026 09:40:00 +0200

Pseudo-off-topic post today.

I wrote a long time ago a post about my interest in 2D graphics, what is known as pixel art, including a few resources about it. What happened back then, and still happens now, is that it feels quite relaxing, zen-like, to be drawing one pixel at …

Today's Custom Harness Is Tomorrow's Skill

Kartones — Sun, 09 Aug 2026 18:00:00 +0200

Introduction

I firmly believe in tool composition. Dedicated tools are good, but the moment one tool tries to do too much, it becomes bloated with features and, almost always, speed and quality degrade. Agentic tools are no exception, and now everyone wants to build their custom agent harness, their custom …

Book Review: CLI

Kartones — Sat, 01 Aug 2026 21:20:00 +0200

2026-10-11 Udate: Clarification from the book's author that the diagrams and tables are on purpose terminal-like.

Review

Title: CLI: A Practical Guide to Creating Modern Command-Line Interfaces

Author(s): Derick Schaefer

The presentation of the book is different. In general, formatting is what you would expect from a technical book …

Adopting llms.txt for my blog

Kartones — Mon, 20 Jul 2026 20:00:00 +0200

The scenario

From time to time, my blog gets fully crawled. It used to be mostly Google, and a few times Bing. Lately, I still have one or two full-site crawls per month, and I've noticed an increase in requests with referrers such as chatgpt.com, duck.ai, gemini.google …

A Simple AI Evals Runner

Kartones — Sun, 12 Jul 2026 15:15:00 +0200

I recently had to explain to a friend what "evals" are. After an "imagine classic software tests, but for AI agents and/or models" explanation, the follow-up questions were several variations of "But how?". So I decided to illustrate it with an example. I quickly wrote a tiny shell script …

Book Review: Tidy First?

Kartones — Mon, 15 Jun 2026 08:00:00 +0200

Review

Title: Tidy First?: A Personal Exercise in Empirical Software Design

Author(s): Kent Beck

This is a short book. Very short, if you exclude the fluff and theory. It circles around 15 tidyings (small refactoring techniques), plus some general topics, like coupling vs decoupling, how to do and sequence …

Learning LLMs Through MicroGPT

Kartones — Sun, 07 Jun 2026 14:10:00 +0200

I am slowly nerd sniping myself into learning more about how Large Language Models work. Improving instructions, skills, and agents is quite interesting on its own, but I am also attracted towards understanding the internals, at least to a basic level.

I had been meaning to look at Andrej Karpathy …

A Small Javascript-to-Go Migration with Claude Code

Kartones — Sat, 16 May 2026 11:50:00 +0200

I have a few scripts that I run daily, mostly focused around processing stats and recreating my dashboards (static HTMLs with a chart viewer). On their latest iteration, I built them in Javascript, and while they serve their purpose, that poses two limitations:

I need to have Node.js installed …

Vampire Crawlers savegame editor

Kartones — Thu, 14 May 2026 18:15:00 +0200

After having played for +130 hours the videogame Vampire Survivors, when the follow up, Vampire Crawlers was recently released, I had to play it.

Now, +20 hours of playtime later I was able to finish it once, and again, like I did with Vampire survivors, I wanted to fiddle around …

How I ensure AI agents actually help in my personal projects

Kartones — Sat, 11 Apr 2026 09:50:00 +0200

UPDATE 2026-10-05: Slight rewording of the recommendations section.

Instead of just saying "LLMs work way better now", I thought that it would be interesting for once to show something more "applied".

First, a screenshot:

This is a GitHub pull request of one of my pet projects (private, at least for …

One workflow across Claude Code, Copilot, and local models

Kartones — Sat, 28 Mar 2026 16:00:00 +0100

Intro

I'm heavily leaning towards agentic-driven development, although done "my way": Focused changes, continuous iteration (including on rules, instructions, subagents, etcetera), and unless it is a simple local script, everything done via TDD. This change also means a significant increase in code reviewing effort. I now code less, but review …

Book Review: AI Engineering

Kartones — Thu, 12 Mar 2026 21:40:00 +0100

Review

Title: AI Engineering: Building Applications with Foundation Models

Author(s): Chip Huyen

This book provides a broad and structured overview of how modern AI systems built on top of large language models actually work. Rather than focusing on specific tools or frameworks, it explains the core concepts behind foundation …

Recent book purchases: x86 Assembly and Go

Kartones — Sat, 28 Feb 2026 16:10:00 +0100

I now prefer almost exclusively digital books, but occasionally, they are available only in paper. The following two are my latest physical purchases:

Something old

The item on the left is the first development book I read, "80X86 Assembly Language", from 1995, which only exists in Spanish. A great book …

Coding Is No Longer My Main Skill

Kartones — Sun, 01 Feb 2026 14:00:00 +0100

Disclaimer: The following reflects personal opinions based on experimentation outside of work.

My Story (the boring part)

I started coding at 13, first in C and later in x86 Assembly, learning mostly from books and magazines. I almost skipped university, out of naivety and overconfidence. Although I didn't finish my …