Skip to content
    About

    Categories

    • Inteligencia Artificial 169
    • Tecnología 144
    • Arquitectura 91
    • Metodologías 75
    • Herramientas 56
    • Desarrollo de Software 54
    • Industria 4.0 25
    • Experiencia de Usuario 21
    • Cómo Instalar 20
    • Startup 15

    Archive

    April 2026

    Filter #1.35 1 #agentes 1 #agentes ia 1 #aider 1 #alignment 1 #alineamiento 1 #amd 1 #anthropic 1 #arquitectura 1 #aws trainium 1 #calibracion 1 #calidad 1
    Runtime-generated UI: the first serious year
    Experiencia de Usuario

    Runtime-generated UI: the first serious year

    La idea de que la UI se genere sobre la marcha en lugar de ser prediseñada llegó a producción en 2025. Tras un año de casos reales, el balance es más matizado que el entusiasmo inicial.

    177 6 min April 28, 2026 4.2
    DPO and alternatives to RLHF: practical state in 2026
    Inteligencia Artificial

    DPO and alternatives to RLHF: practical state in 2026

    Direct Preference Optimization and its relatives have displaced RLHF as the preferred alignment method in much of the ecosystem. This is the practical state of the field in 2026.

    254 5 min April 28, 2026 4.7
    Kubernetes 1.35 GA: an operations-side balance sheet
    Arquitectura

    Kubernetes 1.35 GA: an operations-side balance sheet

    Kubernetes 1.35 llega a GA en 2026 consolidando mejoras gestadas durante tres versiones. Este es el balance desde la operación diaria: qué usar, qué probar y qué evitar.

    115 9 min April 28, 2026 4.8
    AI editors in 2026: comparison after a year of use
    Desarrollo de Software

    AI editors in 2026: comparison after a year of use

    Claude Code, Cursor, Aider, Copilot, Windsurf. Tras un año intenso con los principales editores asistidos por IA, esta es la comparativa que importa para quien elige hoy.

    128 5 min April 28, 2026
    Skills and subagents: the agent reuse pattern
    Arquitectura

    Skills and subagents: the agent reuse pattern

    Skills package reusable capabilities; subagents isolate bounded-task execution. Together they form the most effective pattern for composing complex agents in 2026.

    193 5 min April 28, 2026 4.5
    NVIDIA alternatives in 2026: where the market is heading
    Tecnología

    NVIDIA alternatives in 2026: where the market is heading

    NVIDIA domina el entrenamiento de IA, pero la inferencia tiene cada vez más alternativas viables. Este es el mapa del ecosistema en 2026.

    158 5 min April 28, 2026 4.7
    Synthetic training data in 2026: when it works
    Inteligencia Artificial

    Synthetic training data in 2026: when it works

    Synthetic data has moved from precarious substitute for real data to central component of modern training. These are the patterns that work and those still failing.

    70 5 min April 28, 2026 4.3
    MCP as multi-vendor standard: patterns already mature
    Arquitectura

    MCP as multi-vendor standard: patterns already mature

    The Model Context Protocol, proposed by Anthropic in late 2024 and adopted through 2025-2026 by every major vendor, has proven operational patterns. This is the state of the art.

    100 5 min April 28, 2026 4.5
    Mature LLM-as-judge: when to trust and when not
    Inteligencia Artificial

    Mature LLM-as-judge: when to trust and when not

    Using an LLM to judge another LLM became widespread in 2024 and remains the only scalable way to evaluate qualitative quality. The mature question is when to trust those numbers.

    77 5 min April 28, 2026 4.7
    Claude Sonnet 4.6 in production: the cost-quality balance
    Inteligencia Artificial

    Claude Sonnet 4.6 in production: the cost-quality balance

    Sonnet 4.6 es el modelo por defecto de la mayoría de cargas de trabajo en 2026. Estos son los casos donde brilla, dónde no basta y por qué sigue siendo el sweet spot.

    86 5 min April 28, 2026 4.3
    Hybrid RAG in 2026: the patterns that keep winning
    Arquitectura

    Hybrid RAG in 2026: the patterns that keep winning

    Tres años después del boom inicial, el RAG en producción ha convergido en patrones híbridos que combinan búsqueda densa, léxica y reranking. Estos son los que sobreviven al paso del tiempo.

    180 5 min April 28, 2026 4.6
    How to install Coolify on Docker (2026 step-by-step guide)
    Cómo Instalar

    How to install Coolify on Docker (2026 step-by-step guide)

    Coolify es una plataforma autohospedada que replica la experiencia de Vercel o Heroku sobre tu propia infraestructura. Esta guía instala Coolify 4.x paso a paso con Docker en Ubuntu 24.04.

    252 14 min April 28, 2026 4.7

    Posts pagination

    1 2 3 Next
    Javier Cañete Arroyo — JACAR La marca JACAR toma las dos primeras letras de cada parte del nombre: JAvier, CAñete, ARroyo. CEO · FUNDADOR JAvierCAñeteARroyo JACAR JAvier · CAñete · ARroyo

    Production notes on technology, DevOps, and AI from Madrid.

    LinkedIn RSS Jacar Systems

    Explore

    • Inteligencia Artificial 169
    • Tecnología 144
    • Arquitectura 91
    • Metodologías 75
    • Herramientas 56
    • Desarrollo de Software 54

    Latest

    • Multi-agent systems: LangGraph vs CrewAI vs Autogen in 2026 14 May 2026
    • What PegaProx adds over the Proxmox VE 9 GUI 14 May 2026
    • How to build a production-ready agent with the Anthropic SDK, step by step 12 May 2026
    • Claude Code vs Cursor vs GitHub Copilot in 2026: a comparison with measured tasks 8 May 2026

    Connect

    Say hello hola@jacar.es
    Location
    Madrid, ES
    Languages
    ES · EN
    Archive
    440 entries
    Topics #agentes ia #llm #anthropic #ia #agentes #observabilidad #devops #kubernetes #seguridad #contenedores #ia generativa #industria 4.0 #rag #openai #inteligencia artificial #deep-learning
    © 2026 Jacar Systems S.L. · made with in · Madrid, Spain Systems operational
    Privacy Cookies RSS Search
    Manage Consent
    To provide the best experiences, we use technologies like cookies to store and/or access device information. Consenting to these technologies will allow us to process data such as browsing behavior or unique IDs on this site. Not consenting or withdrawing consent, may adversely affect certain features and functions.
    Functional Always active
    The technical storage or access is strictly necessary for the legitimate purpose of enabling the use of a specific service explicitly requested by the subscriber or user, or for the sole purpose of carrying out the transmission of a communication over an electronic communications network.
    Preferences
    The technical storage or access is necessary for the legitimate purpose of storing preferences that are not requested by the subscriber or user.
    Statistics
    The technical storage or access that is used exclusively for statistical purposes. The technical storage or access that is used exclusively for anonymous statistical purposes. Without a subpoena, voluntary compliance on the part of your Internet Service Provider, or additional records from a third party, information stored or retrieved for this purpose alone cannot usually be used to identify you.
    Marketing
    The technical storage or access is required to create user profiles to send advertising, or to track the user on a website or across several websites for similar marketing purposes.
    • Manage options
    • Manage services
    • Manage {vendor_count} vendors
    • Read more about these purposes
    View preferences
    • {title}
    • {title}
    • {title}