Novedades del último mes en eBooks de Informática práctica

From Prototype to Production-Grade LLM Systems. Key Features Get a free one-month digital subscription to www.avaskillshelf.com End-to-end coverage of modern LLMOps, from fundamentals to production deployment and monitoring. Hands-on prompt management, LLM chaining, RAG, and building AI agent examples. Practical insights into LLMOps observability and analytics using LangFuse, Fine-tuning, and securing LLMs in real-world environments. Book Description Large Language Models (LLMs) are transforming how organizations build intelligent applications, yet taking them from experimentation to reliable production systems requires a new disciplineLLMOps. Ultimate LLMOps for LLM Engineering offers a comprehensive journey through the principles, tools, and workflows essential for operationalizing LLMs with confidence and efficiency. It begins by demystifying LLM fundamentals, model behavior, and the evolving landscape of MLOps, giving readers the context needed to design scalable AI systems. The core chapters dive into hands-on techniques that drive real-world LLM applications, including prompt management, LLM chaining, and Retrieval Augmented Generation (RAG). You will explore how to design LLM pipelines, build effective agentic systems, and orchestrate complex multi-step reasoning workflows. Each concept is supported with practical insights applicable across industries and platforms. Moving deeper into production, the book equips you with strategies for deploying, serving, and monitoring LLMs in modern cloud and hybrid environments. You will learn how to fine-tune and adapt models, enforce security and privacy requirements, and detect model drift in dynamic data ecosystems. What you will learn Understand LLM foundations and how they integrate with the MLOps ecosystem. Build robust prompt strategies, LLM chains, and RAG pipelines for complex workflows. Design and deploy AI agents and autonomous LLM-driven systems. Serve, scale, monitor, and evaluate LLMs across cloud and on-prem environments. Apply fine-tuning, optimization, and adaptation techniques to improve model performance. Implement best practices for LLM security, privacy, governance, and drift detection. Who is This Book For? This book is tailored for GenAI Developers, Machine Learning Engineers, and Data Scientists who want to build, deploy, and manage LLM-powered systems at scale. Readers should have foundational knowledge of AI/ML concepts, basic NLP familiarity, and experience with Python programming to fully benefit from the content. Table of Contents 1. Unveiling the World of Large Language Models 2. Getting Started with MLOps 3. Mastering Prompt Management for LLMs 4. The Power of LLM Chaining 5. Retrieval Augmentation Generation 6. AI Agents and Autonomous Systems 7. Deploying Large Language Models 8. Model Monitoring and Evaluation 9. LLM Fine-tuning and Adaptation 10. LLM Security, Privacy, and Drift Detection 11. LLMOps with Langfuse 12. Real-World Examples and Emerging Trends Index

The AWS Certified Cloud Practitioner (CLF-C02) Exam is your gateway to todays cloud-first worldand Ultimate AWS Certified Cloud Practitioner (CLF-C02) Certification Guide (2nd Edition) is your complete roadmap for clearing it with confidence. Whether you are starting from scratch or strengthening your IT foundation, this book prepares you to succeed in the worlds most recognized cloud certification. You begin with a solid grounding in cloud computing fundamentals, and gradually advance into AWS global infrastructure, compute, storage, databases, networking, migration, security, pricing, governance, and application integration. Each chapter simplifies complex topics with illustrations, real-world business examples, hands-on walkthroughs, and structured explanations aligned with the CLF-C02 exam blueprint. Practice questions, exam tips, and review sections help you reinforce learning and identify the weak areas, ensuring that you are always exam-ready!

When Microsoft released early versions of Windows, they included simple games like Solitaire and Minesweeper. For decades, millions of office workers lost countless hours to these digital distractions. But these games were not included merely for entertainment; they were covert training programs designed to rewire human muscle memory.This technological history uncovers the brilliant user-interface strategy behind early operating systems. In the early 1990s, the computer mouse was an alien concept. Solitaire was specifically engineered to teach users the fluid mechanics of "drag and drop," while Minesweeper was designed to train speed and precision with the "left and right click."By examining the diaries of early software engineers, the book reveals how these simple games bridged the massive psychological gap between analog typewriters and digital interfaces. It explores how hidden gamification successfully taught an entire generation a new language of physical interaction without them ever realizing they were in a classroom.Revisit the grey screens that shaped our digital dexterity. This narrative proves that the most effective technological revolutions are the ones disguised as pure play.

Em um mundo de complexidade e velocidade tecnológicas, a documentação é um ativo estratégico que impulsiona produtos e eleva a experiência do usuário. Este livro é o seu guia prático para dominar a a

Un llamamiento inaplazable para poner freno a la carrera hacia la superinteligencia. «Un libro muy interesante, incluso si no estás de acuerdo con su conclusión.» Marta Peirano, periodista y escritor

In the tech industry, "frictionless" is the ultimate buzzword. Designers spend millions optimizing apps to ensure that purchasing, subscribing, or transferring money requires nothing more than a casual glance or a single, effortless tap of the thumb.But this obsession with removing barriers has created a catastrophic vulnerability. By eliminating the natural pauses that once forced consumers to stop and think, frictionless design has inadvertently paved a golden highway for scammers, making it easier than ever to trick the brain into making irreversible financial mistakes.Seamless Deception investigates the dangerous intersection of behavioral psychology and user interface design. It reveals how the very mechanics designed to make our lives easier are being weaponized by bad actors to bypass our cognitive defenses and empty our wallets with terrifying speed.Rethink the value of inconvenience in the digital age. Learn how to recognize manipulative design patterns, implement necessary friction into your digital life, and protect your assets from the hidden dangers of an overly optimized world.

Data visualization turns complex data into insight, alignment, and actionand it is a core skill for modern data, analytics, and engineering roles. Prompting Python Data Visualization shows you how to design clear, trustworthy visuals in Python, while accelerating the entire workflow by translating natural-language intent into working visualization code with AI. You begin with the foundations of visual thinking and data handling, then build strong technical skills using Matplotlib and Seaborn. The book takes you from basic plots to advanced layouts, styling, annotations, time-series analysis, and publication-ready exports, grounded in real-world analytics and reporting use cases. As you progress, you learn prompt engineering techniques to generate charts with AI, refine and debug AI-produced code, and automate repetitive visualization tasks using reusable prompt templates. By the end of the book, you will produce professional visuals for reports, notebooks, and dashboards with speed, consistency, and confidence.

In the lucrative world of digital loot boxes and card packs, players believe they are at the mercy of pure, mathematical randomness. They grind for hours or spend real money hoping for a legendary drop, completely unaware that the game is actively monitoring their frustration levels. To prevent players from quitting after a streak of bad luck, developers implemented a brilliant psychological safety net: the Pity Timer.This hidden code tracks exactly how many times you have failed to receive a high-value reward. As your losing streak extends, the algorithm quietly manipulates the odds in your favor behind the scenes. Eventually, the Pity Timer hits its threshold and guarantees a legendary drop, providing a massive dopamine hit exactly when you were about to abandon the game.Pity Timer Mechanics dissects the sophisticated behavioral engineering used to keep players addicted. It exposes how pseudo-randomness is weaponized to maintain the illusion of luck while strictly controlling the digital economy.Understand the invisible rules governing your favorite games. By recognizing the mathematical strings pulling your emotions, you can break the cycle of digital slot machines and regain control over your spending habits.

Em um mundo cada vez mais conectado e automatizado, e com a proliferaço do uso de inteligencia artificial, o bom funcionamento dos dispositivos eletronicos, especialmente os que compem o ecossistema IoT, tornou-se essencial para a segurança, para a produtividade e ate para a sobrevivencia humana. Este livro sugere um modelo conceitual e tecnico que prope o monitoramento da "saude" de dispositivos inteligentes com base na analise multidimensional e temporal de seus parametros eletricos. A analise de dados funcionais por meio da criaço de matrizes multidimensionais sobrepostas permite organizar e monitorar dados como corrente, tenso, potencia, consumo e fator de potencia ao longo do tempo e de formas diferentes. O autor prope uma abordagem para inferir, de forma visual e objetiva, mediante algoritmos, o indice de saude de um dispositivo. O modelo oferece tambem uma representaço grafica comparavel a um "raio X digital", revelando o estado interno do equipamento com base em variaçes sutis de desempenho e desgaste de seus componentes eletronicos. O livro foi dividido em duas partes. Uma delas, a mais ludica, diz respeito a comparaço entre o funcionamento de um corpo humano e um dispositivo inteligente; e a outra sugere um modelo para obter indicadores da saude dos dispositivos. O livro no apenas apresenta a sua teoria de uso das matrizes temporais multidimensionais como traz insights de implementaço, desde a prototipagem ate as aplicaçes futuras em manutenço preditiva, redes autonomas e inteligencia embarcada. Assim, em determinados momentos, vamos nos referir a dispositivos de IoT simplesmente como "o IoT". O objetivo e apresentar caminhos alternativos para que o leitor possa refletir sobre o papel das maquinas no nosso cotidiano e a necessidade de preservar sua integridade em um mundo onde humanos e sistemas automatizados se tornam cada vez mais interdependentes.

No universo da tecnologia, aprendemos desde cedo a valorizar o que pode ser medido: linhas de código, entregas, certificações, frameworks dominados. Mas, à medida que avançamos na carreira, uma verda

En plena revolución de la inteligencia artificial, la humanidad comienza a redescubrir una verdad incómoda y fascinante: la mente neurodivergente no es una desviación de la norma, sino una fuente inagotable de creatividad, velocidad cognitiva y pensamiento disruptivo que el mundo empieza a necesitar con urgencia.Mentes aceleradas propone una mirada renovada sobre el TDAH (Trastorno por Deficit de Atencion con Hiperactividad), no como un trastorno, sino como un estilo cerebral singular, capaz de detectar patrones, generar ideas originales y adaptarse a entornos cambiantes con una agilidad que las maquinas apenas logran imitar.Con base en la neurociencia contemporanea, en casos reales y en una profunda reflexion sobre el impacto cultural de la IA, el doctor Javier Pou Ucha revela como muchas de las cualidades historicamente señaladas como "problematicas" atencion no lineal, impulsividad creativa, busqueda constante de novedad, sensibilidad emocional se transforman hoy en ventajas estrategicas en una era cada vez mas digital.Este libro es para quienes vislumbran que pensar distinto es una forma de inteligencia, y tambien para aquellos que creen que el futuro sera de las mentes capaces de cuestionar, romper el molde y atreverse a imaginar nuevas posibilidades.

Generative AI is rapidly transforming how organizations create content, build intelligent systems, and automate complex tasks. Understanding how these models workand how to build themis now a career-defining skill for developers and data professionals. Mastering Generative AI Systems Engineering begins with the core foundations of generative AI. You will explore the essential mathematics, latent spaces, probability concepts, and neural network principles behind VAEs and GANs. The book then guides you through advanced systems such as CycleGANs, StyleGANs, and cutting-edge Diffusion Modelsthe engines behind todays most powerful generative tools.

Un libro imprescindible para desenmascarar las falsas promesas de la inteligencia artificial y entender cómo las grandes tecnológicas convierten su hype en un negocio a costa de nuestras vidas.¿Va a acabar la inteligencia artificial dominando el mundo? ¿Han creado los cientificos una forma de vida artificial capaz de pensar por si misma? ¿Va a quedarse con nuestros puestos de trabajo? ¿Estamos entrando en una era en la que los ordenadores son mejores que los humanos? Las doctoras Emily M. Bender y Alex Hanna responden a todas estas preguntas con un rotundo NO, con frases sarcasticas como Ya les gustaria o simplemente riendose. Estos temores no son mas que una consecuencia de la implacable promocion la IA por parte de las empresas tecnologicas para justificar el robo de datos, motivar la creacion de herramientas de vigilancia en el puesto de trabajo y devaluar la creatividad humana. En La estafa de la IA encontraremos ejemplos reales, argumentos claros y opiniones de expertos que nos proporcionaran las herramientas para detectar el hype de la IA en todas y cada una de sus manifestaciones. Ya que, al descubrir la explotacion que hay detras de su implantacion y la usurpacion de poder que pretende ocultar, seremos capaces de disipar el humo que nos intentan vender, tanto en el trabajo como en nuestra vida cotidiana.

In recent years, Natural Language Processing (NLP) has gone through a radical breakthrough due to the success of Large Language Models (LLMs). These models have demonstrated that an unsupervised inductive approach, based on processing large amounts of raw data, can achieve extraordinary accuracy rates in many NLP-related tasks. This progress seems to have reduced the role of theoretical linguistics in computational approaches to linguistic analysis. For instance, metalinguistic annotation, a central element in supervised learning, which traditionally relies on established linguistic theories, has lost its core place in eveloping trained models for different NLP tasks.In this context, a closer dialogue between theoretical and computational linguistics becomes essential to integrate theoretical and practical perspectives, bridging the gap between these two approaches to language study. This is particularly important for both the practical implementation of linguistic theories in computational models and the theoretical interpretation of results produced by NLP systems. This special issue of the Italian Journal of Computational Linguistics aims to bridge this gap by exploring the emerging synergies between theoretical linguistics and computational linguistics and the implications these have for the future of the two approaches.

"IAÊ, ROBÔ? – Inteligência Artificial para Humanos de Verdade" é um convite para conversar sobre inteligência artificial como se fosse um papo de sala de aula, café ou sofá, sem jargões nem medo desn

Una guía para entender cómo la inteligencia artificial aumenta las capacidades humanas y se convierte en una verdadera aliada.¿La inteligencia artificial viene a desplazarnos? ¿A quitarnos el trabajo? ¿O viene a aumentar -como nunca antes- las capacidades que nos hacen humanos?En medio de promesas exageradas y noticias apocalipticas, Fredi Vivas -ingeniero, tecnologo y pionero en IA- nos propone una mirada distinta: lo humano y lo artificial ya no compiten, sino que se integran. En este libro traza el mapa de una nueva era, donde pensar, crear y decidir ya no es una tarea individual, sino un proceso compartido con maquinas inteligentes. Ademas, nos explica, de manera clara y accesible, como funciona este nuevo paradigma y por que nos involucra a todos. A traves de historias reales de cientificos que descubren nuevas proteinas, artistas que crean con la ayuda de la IA y docentes que enseñan junto con asistentes inteligentes, el autor nos muestra como la tecnologia se convierte en una extension de nuestra mente.Generacion IA no es un libro tecnico ni futurista. Es una guia para entender el presente y prepararse para lo que viene. Con una mirada etica, humana y realista, Fredi Vivas nos invita a dejar de temerle a la tecnologia y empezar a usarla como lo que es: una aliada.

A Série Universitária foi desenvolvida pelo Senac São Paulo com o intuito de preparar profissionais para o mercado de trabalho. Os títulos abrangem diversas áreas, abordando desde conhecimentos teóri

La integración de las Tecnologías de la Información y la Comunicación (TIC) y más particularmente Inteligencia Artificial (IA) y los Sistemas Expertos (SE) en el contexto educativo, incorporan un importante tema de accion y reflexion para los profesionales de la educacion. De hecho, los tomadores de decisiones, cientificos y docentes en el campo cuestionan el lugar que ocupa la tecnologia digital y los medios a implementar para integrarla con exito, lo que a veces resulta sumamente complejo. Nuevas tecnologias digitales estan apareciendo cada vez mas rapidamente en las instituciones educativas. Este es particularmente el caso de la IA, integrada masivamente en las escuelas de America del Norte y Europa. El uso e integracion de esta herramienta, relativamente reciente en el ambito escolar, exige una reflexion critica con relacion a las practicas tecnopedagogicas de los docentes y de sus procesos de integracion inherentes.Los autores de este libro nos presentan sus investigaciones elaboradas sobre el tema de los SE y su relacion con la IA. Por otro lado, utilizan como via a los SE para concretar esta integracion. Las investigaciones de estos estudiosos demuestran que los procesos de integracion se construyen gradualmente y que un analisis cuidadoso de los mismos permitiria comprender las diversas realidades tecnopedagogicas que actuan en las instituciones educativas.

De Newton à Inteligência Artificial é uma jornada intelectual e sensível pela história do pensamento científico — da maçã que caiu sobre Newton aos algoritmos que hoje aprendem conosco. Misturando fí

Art as a compass for democracy in times of technological changeCulture Codes Democracy is a timely publication exploring how art and cultural critique can help societies rethink their relationship to new technologies. Drawing on the expertise of leading European cultural institutions, it highlights the role of artistic practice in shaping democratic futures. The book distinguishes itself through: Three thematic sectionsMediated Realities, Speculative Governance, and Hybrid Entitieseach showing how art engages with technology and democracy Contributions from pioneering cultural organisations, offering real-world case studies and insights A forward-looking perspective, envisioning how art can guide Europe towards digital sovereignty Richly illustrated and thought-provoking, this critical reader is essential for anyone interested in the intersection of art, politics, and technology in shaping tomorrows democracy.