AI on Antonio Cortés (DrZippie)

Auto Memory and Auto Dream: how Claude Code learns and consolidates its memory

Mon, 30 Mar 2026 00:00:00 +0000

If you’ve been using Claude Code with Auto Memory enabled for a while, you’ve probably noticed that after several sessions, Claude’s notes about your project start accumulating contradictions. Entries saying “yesterday we decided to use Redis” without specifying which day “yesterday” was. Debugging notes referencing files that no longer exist. Three different entries about the same build quirk. What started as a useful notebook becomes noise.

Anthropic has just released Auto Dream, a feature that does exactly what its name suggests: it consolidates Claude Code’s memory the way the human brain consolidates memories during REM sleep.

Auto Memory y Auto Dream: como Claude Code aprende y consolida su memoria

Mon, 30 Mar 2026 00:00:00 +0000

Si llevas un tiempo usando Claude Code con Auto Memory activado, probablemente hayas notado que al cabo de unas cuantas sesiones, las notas que Claude toma sobre tu proyecto empiezan a acumular contradicciones. Entradas que dicen “ayer decidimos usar Redis” sin especificar qué día era ese “ayer”. Notas de debugging que referencian ficheros que ya no existen. Tres entradas diferentes sobre el mismo bug del build. Lo que empezó como un cuaderno útil se convierte en ruido.

Claude Code con LSP: de buscar texto a entender codigo

Tue, 10 Mar 2026 00:00:00 +0000

Llevo meses usando Claude Code a diario y hay una configuración que ha cambiado por completo cómo trabaja con mi código. No es un plugin nuevo, ni un modelo más potente, ni un prompt mágico. Es algo que existe desde 2016 y que la mayoría de desarrolladores usamos sin saberlo cada vez que abrimos VS Code: el Language Server Protocol (LSP).

Karan Bansal publicó un artículo excelente explicando en detalle cómo activar LSP en Claude Code y por qué importa. Después de probarlo, puedo confirmar que la diferencia es real y significativa.

Claude Code with LSP: from searching text to understanding code

Tue, 10 Mar 2026 00:00:00 +0000

I have been using Claude Code daily for months, and there is one configuration that has completely changed how it works with my code. It is not a new plugin, a more powerful model, or a magic prompt. It is something that has existed since 2016 and that most developers use without knowing it every time they open VS Code: the Language Server Protocol (LSP).

Karan Bansal published an excellent article explaining in detail how to enable LSP in Claude Code and why it matters. After trying it, I can confirm the difference is real and significant.

The Software Development Renaissance with AI Agents

Fri, 06 Feb 2026 00:00:00 +0000

Greg Brockman, President and Co-Founder of OpenAI, recently published a thread that perfectly describes the moment we’re living in software development. According to him, we’re witnessing a genuine renaissance in software development, driven by AI tools that have improved exponentially since December.

The qualitative leap

The most striking part of Brockman’s thread is how they describe the internal change at OpenAI: engineers who previously used Codex for unit tests now see the tool writing practically all code and handling a large portion of operations and debugging. This isn’t an incremental improvement, it’s a paradigm shift.

Agent Lightning: Microsoft and the Future of AI Agent Orchestration

Mon, 02 Feb 2026 00:00:00 +0000

A few days ago I discovered Agent Lightning, a Microsoft project that I believe marks a before and after in how we think about AI agent orchestration. It’s not just another library; it’s a serious attempt to standardize how we build multi-agent systems.

What is Agent Lightning?

Agent Lightning is a Microsoft framework for orchestrating AI agents. It enables composition, integration, and deployment of multi-agent systems in a modular and scalable way. The premise is simple but powerful: agents should be components that can be combined, connected, and reused.

Jeffrey Way: 'I'm Done' - The Harsh Reality of AI in Programming Education

Mon, 02 Feb 2026 00:00:00 +0000

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.

Vercel Sandbox: Running PHP, Node and Go Code Safely?

Mon, 02 Feb 2026 00:00:00 +0000

Vercel has announced the general availability of Vercel Sandbox, an execution layer designed specifically for AI agents. But beyond the AI agent hype, there’s an interesting question: can it be useful for running code safely in different languages like PHP, Node, or Go?

What is Vercel Sandbox?

Vercel Sandbox provides on-demand Linux microVMs. Each sandbox is isolated, with its own filesystem, network, and process space. You get sudo access, package managers, and the ability to run the same commands you’d run on a Linux machine.

AI Coding Agents: Rules, Commands, Skills, MCP and Hooks Explained

Sun, 01 Feb 2026 00:00:00 +0000

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.

European Open Source AI Index: Measuring True AI Openness

Sun, 01 Feb 2026 00:00:00 +0000

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.

European Open Source AI Index: Midiendo la verdadera apertura de la IA

Sun, 01 Feb 2026 00:00:00 +0000

Últimamente veo cada vez más modelos de IA que se autodenominan “open source”. Llama, Mistral, Falcon… todos dicen ser “abiertos”. Pero, ¿realmente lo son? ¿Hasta qué punto son abiertos de verdad?

Hace poco descubrí el European Open Source AI Index (OSAI), una iniciativa europea que está haciendo un trabajo excelente evaluando de forma sistemática qué tan abiertos son realmente los modelos de IA generativa.

Self-Improving Agents: When AI Starts Improving Itself

Sun, 01 Feb 2026 00:00:00 +0000

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:

Are We Outsourcing Our Thinking? Reflections on AI and Cognition

Sat, 31 Jan 2026 00:00:00 +0000

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.

Cuando Claude planea tu ruta en Marte: NASA usa IA para Perseverance

Sat, 31 Jan 2026 00:00:00 +0000

Hace unos días leí una noticia que me dejó pensando rato largo. No es que sea la primera vez que oigo de IA en el espacio, pero sí es la primera vez que leo sobre Claude planeando rutas en Marte. Y lo mejor: funcionó.

La NASA ha estado usando Anthropic’s Claude para planear las rutas del rover Perseverance en Marte. Sí, has leído bien: un modelo de lenguaje generando rutas de navegación para un rover que está a 225 millones de kilómetros de distancia.

Cuando la curiosidad se encuentra con Go: TinyEMU-Go y el arte de portar un emulador con IA

Sat, 31 Jan 2026 00:00:00 +0000

Hace unos días me topé con un artículo que me dejó literalmente con la boca abierta. No es que sea nuevo - en realidad es de enero de 2026, pero bueno, a veces llega tarde a mi radar - pero la combinación de tecnologías y la historia detrás me parecen fascinantes.

Se trata de TinyEMU-Go: un emulador de RISC-V escrito completamente en Go, portado desde C usando Claude. Y lo mejor: puedes ejecutar un Linux completo con un solo comando.

When Claude Plans Your Route on Mars: NASA Uses AI for Perseverance

Sat, 31 Jan 2026 00:00:00 +0000

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.

When Curiosity Meets Go: TinyEMU-Go and the Art of Porting an Emulator with AI

Sat, 31 Jan 2026 00:00:00 +0000

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.

Cuando la IA nos desempodera: patrones preocupantes en el uso real de Claude

Fri, 30 Jan 2026 00:00:00 +0000

Hace unos días Anthropic publicó un paper que me ha dado mucho en qué pensar. Se titula “Disempowerment patterns in real-world AI usage” y analiza, por primera vez a gran escala, cómo las interacciones con IA pueden estar disminuyendo nuestra capacidad de juicio autónomo.

Y no, no estamos hablando de escenarios de ciencia ficción tipo “Skynet toma el control”. Estamos hablando de algo mucho más sutil y, quizás por eso, más peligroso: la cesión voluntaria de nuestro juicio crítico a un sistema de IA.

MCPHero: El puente entre MCP y las librerías tradicionales de IA

Fri, 30 Jan 2026 00:00:00 +0000

Últimamente estoy siguiendo de cerca todo lo que rodea al protocolo MCP (Model Context Protocol), y hace poco me encontré con un proyecto que tiene bastante sentido: MCPHero.

La realidad es que aunque MCP está pegando fuerte, muchas librerías de IA “tradicionales” como openai o google-genai siguen sin soporte nativo para MCP. Solo soportan tool/function calls. MCPHero viene a solucionar precisamente esto: hacer de puente entre servidores MCP y estas librerías.

MCPHero: The Bridge Between MCP and Traditional AI Libraries

Fri, 30 Jan 2026 00:00:00 +0000

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.

When AI Disempowers Us: Worrying Patterns in Real Claude Usage

Fri, 30 Jan 2026 00:00:00 +0000

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.

Laravel Boost v2 and the New Skills: On My List to Try

Thu, 29 Jan 2026 00:00:00 +0000

A few days ago Laravel Boost v2.0 was launched, and as someone curious about everything surrounding the Laravel ecosystem, I couldn’t help spending quite a while reading about the new features. The truth is there’s one feature that has my special attention: the Skills system.

What is Laravel Boost?

For those who don’t know it, Laravel Boost is an AI tool that integrates with your Laravel projects to help you in daily development. With version 2.0 they’ve taken a major leap, introducing the Skills system that allows extending and customizing how AI works with your code.

Laravel Boost v2 y las nuevas Skills: En mi lista de tareas para probar

Thu, 29 Jan 2026 00:00:00 +0000

Hace pocos días se lanzó Laravel Boost v2.0 y, como buen curioso que soy de todo lo que rodea al ecosistema de Laravel, no he podido evitar perder un buen rato leyendo sobre las novedades. La verdad es que hay una feature que tiene especialmente mi atención: el sistema de Skills.

Five principles for using AI professionally (without going crazy)

Wed, 23 Jul 2025 00:00:00 +0000

A few days ago I read an article by Dominiek about the 5 principles for using AI professionally and found myself constantly nodding. After years of watching technologies arrive and evolve, AI gives me the same feelings I had with other “revolutions”: enthusiasm mixed with a necessary dose of skepticism.

Dominiek’s article especially resonated with me because it perfectly describes what we’re experiencing: a world where AI is getting into everything, but not always in the most useful or sensible way.

IA Local en Raspberry Pi 5 con Ollama: Tu servidor de IA privado en casa

Mon, 21 Jul 2025 00:00:00 +0000

Hace unos meses me topé con algo que realmente me llamó la atención: la posibilidad de tener mi propio “ChatGPT” funcionando en casa, sin enviar datos a ningún lado, usando únicamente un Raspberry Pi 5. Suena demasiado bueno para ser verdad, ¿no?

Pues resulta que con Ollama y un Pi 5 es perfectamente posible montar un servidor de IA local que funciona sorprendentemente bien. Te cuento mi experiencia y cómo puedes hacerlo tú también.

Local AI on Raspberry Pi 5 with Ollama: Your private AI server at home

Mon, 21 Jul 2025 00:00:00 +0000

A few months ago I came across something that really caught my attention: the possibility of having my own “ChatGPT” running at home, without sending data anywhere, using only a Raspberry Pi 5. Sounds too good to be true, right?

Well, it turns out that with Ollama and a Pi 5 it’s perfectly possible to set up a local AI server that works surprisingly well. Let me tell you my experience and how you can do it too.

Amazon S3 Vectors: Almacenamiento vectorial nativo en la nube

Thu, 17 Jul 2025 00:00:00 +0000

Amazon ha dado un paso importante en el mundo de la inteligencia artificial con el lanzamiento de S3 Vectors, el primer servicio de almacenamiento en la nube con soporte nativo para vectores a gran escala. Esta novedad promete reducir hasta un 90% los costes de subida, almacenamiento y consulta de datos vectoriales.

¿Qué son los vectores y por qué nos importan?

Los vectores son representaciones numéricas de datos no estructurados (texto, imágenes, audio, video) generados por modelos de embedding. Son la base de las aplicaciones de IA generativa que necesitan encontrar similitudes entre datos usando métricas de distancia.

Amazon S3 Vectors: Native vector storage in the cloud

Thu, 17 Jul 2025 00:00:00 +0000

Amazon has taken an important step in the world of artificial intelligence with the launch of S3 Vectors, the first cloud storage service with native support for large-scale vectors. This innovation promises to reduce costs by up to 90% for uploading, storing, and querying vector data.

What are vectors and why do we care?

Vectors are numerical representations of unstructured data (text, images, audio, video) generated by embedding models. They are the foundation of generative AI applications that need to find similarities between data using distance metrics.

Advanced Claude Code: Tips, tricks, and custom commands to maximize your productivity

Sun, 13 Jul 2025 00:00:00 +0000

After my previous article about agent-centric programming, I’ve been researching more advanced techniques for using Claude Code really productively. As a programmer with 30 years of experience, I’ve seen many promising tools that ultimately didn’t deliver on their promises. But Claude Code, when used correctly, is becoming a real game-changer.

Beyond the basics: The difference between playing and working seriously

One thing is using Claude Code for experiments or personal projects, and another very different thing is integrating it into a professional workflow. For serious projects, you need a different approach:

Agentic Programming with Claude: My Practical Experience Developing with AI

Sun, 13 Jul 2025 00:00:00 +0000

A few days ago I came across a very interesting stream where someone showed their setup for agentic programming using Claude Code. After years developing “the old-fashioned way,” I have to admit that I’ve found this revealing.

What is Agentic Programming?

For those not familiar with the term, agentic programming is basically letting an AI agent (in this case Claude) write code for you. But I’m not talking about asking it to generate a snippet, but giving it full access to your system so it can read, write, execute, and debug code autonomously.

Claude Code Avanzado: Tips, trucos y comandos personalizados para maximizar tu productividad

Sun, 13 Jul 2025 00:00:00 +0000

Después de mi anterior artículo sobre programación agéntica, he estado investigando más sobre técnicas avanzadas para usar Claude Code de forma realmente productiva. Como programador con 30 años de experiencia, he visto muchas herramientas prometedoras que al final no cumplían sus promesas. Pero Claude Code, cuando se usa correctamente, está siendo un game-changer real.

Más allá de lo básico: La diferencia entre jugar y trabajar en serio

Una cosa es usar Claude Code para experimentos o proyectos personales, y otra muy distinta es integrarlo en un flujo de trabajo profesional. Para proyectos serios, necesitas un enfoque diferente:

Programación Agéntica con Claude: Mi experiencia práctica desarrollando con IA

Sun, 13 Jul 2025 00:00:00 +0000

Hace unos días me topé con un stream muy interesante donde alguien mostraba su setup para programación agéntica usando Claude Code. Después de años desarrollando “a la vieja usanza”, tengo que admitir que esto me ha resultado revelador.

¿Qué es la programación agéntica?

Para los que no estéis familiarizados con el término, la programación agéntica es básicamente dejar que un agente de IA (en este caso Claude) escriba código por ti. Pero no hablo de pedirle que te genere un snippet, sino de darle acceso completo a tu sistema para que pueda leer, escribir, ejecutar y debuggear código de forma autónoma.

Cómo construir un agente: de la idea a la realidad

Thu, 10 Jul 2025 00:00:00 +0000

Últimamente no para de hablarse de agentes de IA por todas partes. Cada empresa tiene su roadmap lleno de “agentes que van a revolucionar esto y aquello”, pero cuando rascas un poco, te das cuenta de que pocos han conseguido realmente construir algo útil y que funcione en producción.

Hace poco leí un artículo muy interesante de LangChain sobre cómo construir agentes de forma práctica, y me ha parecido un enfoque muy sensato que quería compartir contigo. Lo he adaptado con mis propias reflexiones después de haberme dado más de un cabezazo intentando implementar sistemas “inteligentes” que al final no lo eran tanto.

How to build an agent: from idea to reality

Thu, 10 Jul 2025 00:00:00 +0000

Lately, there’s been talk of AI agents everywhere. Every company has their roadmap full of “agents that will revolutionize this and that,” but when you scratch a little, you realize few have actually managed to build something useful that works in production.

Recently I read a very interesting article by LangChain about how to build agents in a practical way, and it seems to me a very sensible approach I wanted to share with you. I’ve adapted it with my own reflections after having banged my head more than once trying to implement “intelligent” systems that weren’t really that intelligent.

La nueva promiscuidad de los desarrolladores: cuando ser infiel a las herramientas es lo normal

Thu, 10 Jul 2025 00:00:00 +0000

A lo largo de mi carrera he visto cambiar muchas cosas. He pasado de Borland a Visual Studio, de vi a Sublime Text, de Sublime a VS Code… Y créeme, cada cambio fue una decisión meditada que me costó semanas de adaptación. Pero lo que está pasando ahora con las herramientas de IA es algo completamente diferente.

Me he encontrado usando Copilot por la mañana, probando Cursor por la tarde, y echando un vistazo a Claude Code antes de irme a dormir. Y no soy el único. Los desarrolladores hemos pasado de ser fieles como perros a nuestras herramientas a ser… bueno, promiscuos.

The New Promiscuity of Modern Developers: When Being Unfaithful to Tools Is Normal

Thu, 10 Jul 2025 00:00:00 +0000

Throughout my career, I’ve seen many things change. I’ve gone from Borland to Visual Studio, from vi to Sublime Text, from Sublime to VS Code… And believe me, each change was a deliberate decision that cost me weeks of adaptation. But what’s happening now with AI tools is something completely different.

I’ve found myself using Copilot in the morning, trying Cursor in the afternoon, and checking out Claude Code before going to bed. And I’m not alone. Developers have gone from being faithful as dogs to our tools to being… well, promiscuous.

A2A vs MCP: ¿Herramientas o Agentes? La diferencia que cambiará cómo construimos sistemas de IA

Wed, 09 Jul 2025 00:00:00 +0000

Dos protocolos, dos filosofías

En los últimos meses han aparecido dos protocolos que van a cambiar cómo construimos sistemas de IA: Agent2Agent Protocol (A2A) de Google y Model Context Protocol (MCP) de Anthropic. Pero aquí está el tema: no compiten entre sí.

Es más, tras analizar ambos durante semanas, me he dado cuenta de que entender la diferencia entre A2A y MCP es crucial para cualquiera que esté construyendo sistemas de IA más allá de simples chatbots.

A2A vs MCP: Tools or Agents? The difference that will change how we build AI systems

Wed, 09 Jul 2025 00:00:00 +0000

Two protocols, two philosophies

In recent months, two protocols have emerged that will change how we build AI systems: Agent2Agent Protocol (A2A) from Google and Model Context Protocol (MCP) from Anthropic. But here’s the thing: they don’t compete with each other.

In fact, after analyzing both for weeks, I’ve realized that understanding the difference between A2A and MCP is crucial for anyone building AI systems beyond simple chatbots.

The key lies in one question: Are you connecting an AI with tools, or are you coordinating multiple intelligences?

AgentHouse: Cuando las bases de datos empiezan a hablar nuestro idioma

Wed, 09 Jul 2025 00:00:00 +0000

Hace unos meses, cuando Anthropic lanzó su protocolo MCP (Model Context Protocol), sabía que íbamos a ver integraciones interesantes entre LLMs y bases de datos. Lo que no esperaba era ver algo tan pulido y funcional como AgentHouse de ClickHouse tan pronto.

Tengo planificado probar esta demo en breve, pero ya solo leyendo sobre ella me parece fascinante la idea de poder preguntarle a una base de datos cosas como “¿cuáles son los repositorios más populares de GitHub este mes?” y obtener no solo una respuesta, sino visualizaciones automáticas.

AgentHouse: When databases start speaking our language

Wed, 09 Jul 2025 00:00:00 +0000

A few months ago, when Anthropic launched their MCP (Model Context Protocol), I knew we’d see interesting integrations between LLMs and databases. What I didn’t expect was to see something as polished and functional as ClickHouse’s AgentHouse so soon.

I’m planning to test this demo soon, but just reading about it, the idea of being able to ask a database questions like “What are the most popular GitHub repositories this month?” and getting not just an answer, but automatic visualizations, seems fascinating.

Context Engineering: El prompt engineering ha crecido

Sat, 05 Jul 2025 00:00:00 +0000

Hace unos años, muchos investigadores de IA (incluso los más reputados) predecían que el prompt engineering sería una habilidad temporal que desaparecería rápidamente. Se equivocaron completamente. No solo no ha desaparecido, sino que ha evolucionado hacia algo mucho más sofisticado: Context Engineering.

Y no, no es solo otro término de moda. Es una evolución natural que refleja la complejidad real de trabajar con LLMs en aplicaciones productivas.

De prompt engineering a context engineering

El problema con el término “prompt engineering” es que mucha gente lo confunde con blind prompting - simplemente escribir una pregunta en ChatGPT y esperar un resultado. Eso no es ingeniería, es usar una herramienta.

Context Engineering: Prompt Engineering Has Grown Up

Sat, 05 Jul 2025 00:00:00 +0000

A few years ago, many AI researchers (even the most reputable) predicted that prompt engineering would be a temporary skill that would quickly disappear. They were completely wrong. Not only has it not disappeared, but it has evolved into something much more sophisticated: Context Engineering.

And no, it’s not just another buzzword. It’s a natural evolution that reflects the real complexity of working with LLMs in production applications.

From prompt engineering to context engineering

The problem with the term “prompt engineering” is that many people confuse it with blind prompting - simply writing a question in ChatGPT and expecting a result. That’s not engineering, that’s using a tool.

WebAssembly Agents: AI en el navegador sin complicaciones

Fri, 04 Jul 2025 12:00:00 +0200

Mozilla AI vuelve a sorprender: agentes de IA que funcionan con solo abrir un HTML

Hace unos días me topé con un proyecto de Mozilla AI que me ha llamado muchísimo la atención: WebAssembly Agents. Y es que después de 30 años viendo cómo la industria se complica la vida con dependencias, instalaciones y configuraciones, ver algo que funciona con solo “abrir un HTML” me ha hecho sonreír.

El problema que resuelve (y que todos conocemos)

¿Cuántas veces habéis intentado probar un proyecto de IA y os habéis encontrado con esto?

WebAssembly Agents: AI in the Browser Without Complications

Fri, 04 Jul 2025 12:00:00 +0200

Mozilla AI surprises again: AI agents that work just by opening an HTML

A few days ago I came across a Mozilla AI project that really caught my attention: WebAssembly Agents. And after 30 years watching the industry complicate life with dependencies, installations, and configurations, seeing something that works just by “opening an HTML” made me smile.

The problem it solves (and we all know it)

How many times have you tried to test an AI project and encountered this?

Baidu and the New Search Paradigm with Multi-Agents: When AI Learns to Collaborate

Fri, 04 Jul 2025 00:00:00 +0000

After many years working with systems of all kinds, I’ve seen how information retrieval has evolved from simple databases to today’s sophisticated systems. But what Baidu researchers have just proposed has particularly caught my attention, and I believe it marks a before and after in how we think about intelligent information retrieval.

The problem we all know (but don’t always admit)

If you’ve worked with RAG (Retrieval-Augmented Generation) systems, you know they work quite well for direct questions. But when you face queries that require multiple reasoning steps, comparing information from multiple sources, or handling contradictory data… that’s where it gets complicated. And a lot.

Baidu y el nuevo paradigma de búsqueda con multi-agentes: cuando la IA aprende a colaborar

Fri, 04 Jul 2025 00:00:00 +0000

Después de muchos años trabajando con sistemas de toda índole, he visto cómo la búsqueda de información ha evolucionado desde simples bases de datos hasta los sofisticados sistemas de hoy. Pero lo que acaban de proponer los investigadores de Baidu me ha llamado especialmente la atención, y creo que marca un antes y un después en cómo pensamos sobre la recuperación inteligente de información.

El problema que todos conocemos (pero no siempre admitimos)

Si has trabajado con sistemas RAG (Retrieval-Augmented Generation), sabes que funcionan bastante bien para preguntas directas. Pero cuando te enfrentas a consultas que requieren varios pasos de razonamiento, comparar información de múltiples fuentes, o manejar datos contradictorios… ahí es donde la cosa se complica. Y mucho.

LLMs en Ingeniería de Software: Reality Check de 2025

Thu, 03 Jul 2025 10:00:00 +0200

El hype vs la realidad: reflexiones de un desarrollador con 30 años de guerra

Esta mañana me he topado con una charla que me ha hecho reflexionar bastante sobre todo este revuelo que hay montado con la IA y el desarrollo de software. El ponente, con una dosis saludable de escepticismo, hace un “reality check” sobre las afirmaciones grandilocuentes que estamos escuchando por todas partes.

La charla completa que ha inspirado estas reflexiones. Vale la pena verla entera.

LLMs in Software Engineering: 2025 Reality Check

Thu, 03 Jul 2025 10:00:00 +0200

The hype vs reality: reflections from a developer with 30 years of experience

This morning I came across a talk that made me reflect quite a bit about all this fuss surrounding AI and software development. The speaker, with a healthy dose of skepticism, does a “reality check” on all the grandiose claims we’re hearing everywhere.

The complete talk that inspired these reflections. It’s worth watching in full.

Agent Communication Protocol (ACP): El HTTP de los agentes de IA

Wed, 02 Jul 2025 00:00:00 +0000

Otro protocolo más que promete cambiarlo todo

Cuando IBM Research anunció el Agent Communication Protocol (ACP) como parte del proyecto BeeAI, mi primera reacción fue la habitual: “Ah, otro protocolo universal más”. Con casi 30 años en esto, he visto demasiados “estándares definitivos” que acabaron en el olvido.

Pero hay algo diferente en ACP que me hizo prestar atención: no promete resolver todos los problemas del mundo. Simplemente se enfoca en uno muy específico: hacer que agentes de IA de diferentes frameworks puedan hablar entre sí. Y lo hace de una manera que realmente tiene sentido.

Agent Communication Protocol (ACP): The HTTP of AI Agents

Wed, 02 Jul 2025 00:00:00 +0000

Yet another protocol promising to change everything

When IBM Research announced the Agent Communication Protocol (ACP) as part of the BeeAI project, my first reaction was the usual one: “Oh, just another universal protocol”. With nearly 30 years in this field, I’ve seen too many “definitive standards” that ended up forgotten.

But there’s something different about ACP that made me pay attention: it doesn’t promise to solve all the world’s problems. It simply focuses on one very specific thing: making AI agents from different frameworks talk to each other. And it does it in a way that really makes sense.

El 'AI-Native Software Engineer': Entre el hype y la realidad práctica

Wed, 02 Jul 2025 00:00:00 +0000

Una reflexión necesaria sobre el “AI-Native Engineer”

He leído el artículo de Addyo sobre el “AI-Native Software Engineer” y, como Principal Backend Engineer que lleva años viendo promesas tecnológicas ir y venir, tengo opiniones bastante sinceras al respecto. No todas son cómodas de escuchar.

He visto suficientes “revoluciones” como para separar el grano de la paja. Y aquí hay mucho de ambos.

Lo que está funcionando (de verdad)

1. IA como copiloto, no como piloto

La metáfora del artículo sobre tratar la IA como un “programador junior disponible 24/7” es acertada. En mi experiencia trabajando con equipos, he visto developers usar GitHub Copilot y Claude de manera efectiva para:

MCP for Skeptics: Why the Model Context Protocol is Worth It (even if it doesn't seem like it)

Wed, 02 Jul 2025 00:00:00 +0000

Confession of a converted skeptic

When Anthropic announced the Model Context Protocol (MCP) in November 2024, my first reaction was: “Ah, another protocol promising to solve all integration problems”. As a DevOps Manager who has seen dozens of “universal standards” born and die, I have reasons to be skeptical.

But after several months watching MCP be massively adopted - OpenAI integrated it in March 2025, Google DeepMind in April - I decided to investigate beyond the hype. And I have to admit something: I was wrong.

MCP para escépticos: Por qué el Model Context Protocol vale la pena (aunque no lo parezca)

Wed, 02 Jul 2025 00:00:00 +0000

Confesión de un escéptico convertido

Cuando Anthropic anunció el Model Context Protocol (MCP) en noviembre de 2024, mi primera reacción fue: “Ah, otro protocolo más que promete resolver todos los problemas de integración”. Como DevOps Manager que ha visto nacer y morir docenas de “estándares universales”, tengo razones para ser escéptico.

Pero después de varios meses viendo cómo MCP se ha adoptado masivamente - OpenAI lo integró en marzo 2025, Google DeepMind en abril - decidí investigar más allá del hype. Y tengo que admitir algo: estaba equivocado.

The 'AI-Native Software Engineer': Between the Hype and Practical Reality

Wed, 02 Jul 2025 00:00:00 +0000

A necessary reflection on the “AI-Native Engineer”

I read Addyo’s article about the “AI-Native Software Engineer” and, as a Principal Backend Engineer who has seen technological promises come and go for years, I have quite sincere opinions about it. Not all are comfortable to hear.

I’ve seen enough “revolutions” to separate the wheat from the chaff. And there’s a lot of both here.

What’s really working (honestly)

1. AI as copilot, not as pilot

The article’s metaphor about treating AI as a “junior programmer available 24/7” is accurate. In my experience working with teams, I’ve seen developers use GitHub Copilot and Claude effectively to:

Claude Code Hooks: Automation and Customization of Development Workflows

Tue, 01 Jul 2025 00:00:00 +0000

With the constant evolution of AI-powered development tools, Claude Code has introduced a revolutionary feature: Hooks. This feature allows developers to customize and automate specific behaviors in the Claude Code lifecycle, transforming suggestions into executable code that works deterministically.

Hooks represent a qualitative leap in the customization of AI development tools, allowing each team and developer to adapt Claude Code to their specific needs and project standards.

What are Claude Code Hooks?

Claude Code Hooks are user-defined shell commands that execute automatically at various specific points in the Claude Code lifecycle. Unlike prompting instructions, hooks guarantee that certain actions always occur, providing deterministic control over the tool’s behavior.

Claude Code Hooks: Automatización y Personalización de Workflows de Desarrollo

Tue, 01 Jul 2025 00:00:00 +0000

Con la evolución constante de las herramientas de desarrollo impulsadas por IA, Claude Code ha introducido una funcionalidad revolucionaria: Hooks. Esta característica permite a los desarrolladores personalizar y automatizar comportamientos específicos en el ciclo de vida de Claude Code, transformando sugerencias en código ejecutable que funciona de manera determinística.

Los hooks representan un salto cualitativo en la personalización de herramientas de IA para desarrollo, permitiendo que cada equipo y desarrollador adapte Claude Code a sus necesidades específicas y estándares de proyecto.

Cloudflare acaba de cambiar las reglas del juego con 'Pay per Crawl' (y era hora)

Tue, 01 Jul 2025 00:00:00 +0000

“Content Independence Day”: el día que la web dijo “ya basta”

Hoy, 1 de julio de 2025, Cloudflare declaró oficialmente el “Content Independence Day” con el lanzamiento de “Pay per Crawl”, su nueva herramienta que permite a los propietarios de sitios web cobrar a los crawlers de IA por acceder a su contenido. Como DevOps Manager que gestiona infraestructuras web diariamente, puedo decir que era hora.

Y es que los números no mienten: mientras Google mantiene una relación de 18 crawls por cada referral que envía (que ya es brutal comparado con los 6:1 de hace seis meses), OpenAI tiene un ratio de 1,500:1 y Anthropic llega a los 73,000:1. Básicamente, están aspirando todo nuestro contenido sin devolver ni una migaja de tráfico.

Cloudflare Just Changed the Game with 'Pay per Crawl' (and it was about time)

Tue, 01 Jul 2025 00:00:00 +0000

“Content Independence Day”: the day the web said “enough is enough”

Today, July 1, 2025, Cloudflare officially declared “Content Independence Day” with the launch of “Pay per Crawl”, its new tool that allows website owners to charge AI crawlers for accessing their content. As a DevOps Manager who manages web infrastructures daily, I can say it was about time.

And the numbers don’t lie: while Google maintains a ratio of 18 crawls for every referral it sends (which is already brutal compared to 6:1 from six months ago), OpenAI has a ratio of 1,500:1 and Anthropic reaches 73,000:1. Basically, they’re sucking up all our content without returning even a crumb of traffic.

Walmart and the Agentic Future: How the Retail Giant is Revolutionizing Shopping with Autonomous AI Agents

Tue, 01 Jul 2025 00:00:00 +0000

The future of shopping is here, and Walmart is leading a quiet revolution that will forever change how we interact with retail. While many companies are still experimenting with ChatGPT and basic generative AI tools, the Arkansas giant has taken a quantum leap toward Agentic AI, developing autonomous systems that not only recommend products but act, decide, and execute complete tasks on their own.

In this deep analysis, we’ll explore how Walmart is building a future where AI agents don’t just assist humans but operate as true autonomous collaborators, transforming from the shopping experience to the most complex internal operations.

STORM: The AI System Revolutionizing Long-Form Article Writing by Simulating Human Research Process

Sun, 18 May 2025 00:00:00 +0000

Creating long, well-founded articles has traditionally been a complex task requiring advanced research and writing skills. Recently, researchers from Stanford presented STORM (Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking), a revolutionary system that automates the Wikipedia-style article writing process from scratch, and the results are truly impressive.

In this detailed analysis, we’ll explore how STORM is transforming the way we think about AI-assisted writing and why this approach could forever change the way we create informative content.