Understand AI, one concept at a time.
Direct definitions connected to examples, common mistakes, technical decisions, and verified editorial analysis.
Fundamentals
Basic units, capabilities, and limits for understanding how an AI system works.
Multimodality
Capacidad de procesar o generar más de un tipo de información, como texto, imagen, audio o vídeo.
Parámetro
Valor numérico aprendido durante el entrenamiento que contribuye a transformar entradas en salidas.
Token
Unidad en la que un modelo divide una entrada o salida para procesarla y, a menudo, contabilizar contexto y uso.
Context window
Cantidad máxima de tokens que un modelo puede considerar entre entrada, historial, herramientas y salida en una solicitud.
Models and learning
Architectures, training, and techniques that shape model behaviour.
Fine-Tuning: What Changes When You Continue Training a Model—and What It Does Not Guarantee
Fine-tuning is additional training of a previously trained model to adapt it to a specific objective. This entry explains the process, walks through three examples, and distinguishes the concept from other ways of adapting or using models.
Self-Supervised Learning: What It Is and How It Works
Self-supervised learning creates training objectives from the data itself. This guide explains how the approach works, gives examples from language, vision, and audio, and clarifies its limits and how it differs from other methods.
Aprendizaje por refuerzo con feedback humano
Familia de métodos que usa preferencias humanas para entrenar señales de recompensa y orientar el comportamiento de un modelo.
Synthetic Data: What It Is, How It Is Generated, and What It Does Not Guarantee
Synthetic data is generated artificially to preserve properties of real data that matter for a specific purpose. Its artificial origin does not, by itself, show that it is useful, high-quality, or private.
Knowledge Distillation: How a Student Model Learns from a Teacher—and What It Does Not Guarantee
Distillation transfers training signals from a teacher model to a student. It can take different forms; it does not mean that the student preserves every capability or is more efficient in every environment.
Loss Function: What It Measures During Training—and What It Doesn’t Tell You About a Model
A loss function quantifies the discrepancy between a prediction and a target according to a defined criterion. Understanding what it penalizes—and what falls outside that measure—helps you interpret training without mistaking it for a complete evaluation of the model.
LoRA: How It Adapts a Model with Low-Rank Matrices—and What It Doesn’t Guarantee
LoRA adapts a pretrained model by keeping its original weights fixed and learning additional low-rank matrices. This guide explains the mechanism, compares it with other forms of adaptation, and clarifies what cannot be concluded from the number of trainable parameters alone.
Attention Mechanism: How a Model Relates Different Parts of an Input
Attention is a mathematical operation that combines representations according to their compatibility. This guide explains Q, K, and V, the mechanism’s variants, and its limits—without confusing computational attention with human attention or treating it as an automatic explanation of a model.
Distilled Model: What the Label Means—and What It Does Not Prove
A distilled model is the student produced by a process that transfers some of a teacher model’s behavior. The label describes a training relationship, not a guarantee of equivalence, quality, or efficiency.
Modelo fundacional
Modelo entrenado a gran escala sobre datos amplios y adaptable a múltiples tareas posteriores.
Pretraining: What a Model Learns Before It Is Adapted
Pretraining is a training phase that comes before certain uses or later adaptations. Its objective, data, and relationship to other stages depend on the model: there is no universal recipe, and pretraining alone does not guarantee that a system is reliable.
Sobreajuste
Situación en la que un modelo se adapta demasiado a los datos de entrenamiento y pierde rendimiento ante casos nuevos.
Transformer
Arquitectura neuronal basada principalmente en atención que procesa relaciones entre elementos de una secuencia o varias modalidades.
Generation and interaction
Concepts involved in requesting, controlling, and validating a generated response.
Aprendizaje con pocos ejemplos
Uso de unos pocos ejemplos dentro de la petición para mostrar al modelo la tarea, el criterio o el formato esperado.
In-Context Learning (ICL): How a Model Responds to Prompt Examples
In-context learning lets you guide a model’s response with instructions and examples included in its input. Learn what it means, how to test it, and how it differs from training and related methods, with examples from support, invoices, and customer reviews.
Chain of Thought in AI: What It Is—and What It Doesn’t Prove
A chain of thought is a sequence of intermediate steps expressed in text that a model generates or receives as an example. It can help structure a task and make some steps visible, but coherence does not prove that those steps are correct or faithfully reflect the internal process that produced the answer.
Context Engineering: How to Select and Maintain the Information an AI System Receives
Context engineering means deciding what information a model needs for a task, how to obtain it, and how to keep it relevant while the task is underway. It is not the same as writing a longer prompt: it also involves selecting documents, using tools, and managing state.
Prompt
Conjunto de instrucciones y contexto entregado a un modelo para orientar una tarea y su formato de salida.
Razonamiento en modelos
Capacidad observable de combinar información, restricciones y pasos intermedios para resolver una tarea.
structured output
Respuesta que debe ajustarse a un esquema definido para poder validarse y procesarse de forma automática.
Temperatura
Parámetro de muestreo que modifica la distribución de probabilidad usada para seleccionar los siguientes tokens.
Data and knowledge
How data is represented, retrieved, and connected to verifiable answers.
Vector Database: What It Stores and How Similarity Search Works
A vector database stores numerical representations and retrieves those closest to a query. It does not necessarily generate embeddings or decide on its own which results are relevant.
Búsqueda semántica
Recuperación de información basada en relaciones de significado, normalmente combinada con filtros o búsqueda léxica.
Embedding
Representación numérica que sitúa elementos en un espacio donde ciertas relaciones pueden medirse por proximidad.
Fragmentación de documentos
División de documentos en unidades recuperables que conservan suficiente contexto para responder preguntas.
Primary Source: What It Is, How to Identify It, and What It Can Show
A source is primary in relation to a question when it presents directly the object, data, method, or decision being studied. Its status does not guarantee that it is true, impartial, or sufficient: you still need to assess what it claims and what its limits are.
Generación aumentada por recuperación (RAG)
Patrón que recupera información externa relevante y la incorpora al contexto antes de generar una respuesta.
Grounding
Conexión de una respuesta con datos recuperados, observaciones, herramientas o fuentes externas que pueden comprobarse.
Reranking: What It Is, How It Works, and Its Limits in Retrieval Systems
Reranking is a second scoring stage in retrieval systems that evaluates query–document pairs to refine an initial set of candidates. This glossary entry explains how it works, distinguishes two-stage retrieval from vector search alone, and examines operational limits in RAG and semantic search.
Agents and automation
Tools, memory, and patterns for systems capable of carrying out tasks.
AI Agent: What It Is, How It Works, and How It Differs from a Chatbot
An AI agent is a system that pursues a goal by observing its environment and choosing actions. This guide explains its operating cycle, its limits, and how it differs from a chatbot or a fixed automation.
Llamada a herramientas
Mecanismo por el que un modelo selecciona una operación y propone argumentos estructurados para que la aplicación la ejecute.
Memoria de agente
Mecanismo para conservar y recuperar estado relevante entre pasos o sesiones de un sistema basado en modelos.
Model Context Protocol (MCP): What It Connects, How It Works, and What It Doesn’t Guarantee
MCP is an open integration standard for connecting AI applications to external systems, data, and tools. This guide explains what can be established from the available sources, offers conditional examples, and distinguishes the protocol from an API, tool calling, and an agent.
Assessment
Methods for measuring quality, cost, robustness, and usefulness under reproducible conditions.
AI benchmarks: what they measure and what a score demonstrates
A benchmark is an evaluation defined by tasks, data, a protocol, and metrics. Its score describes performance under those specific conditions; by itself, it proves neither general capability nor production performance.
Contaminación de datos
Presencia total o parcial de datos de evaluación en el entrenamiento, ajuste o contexto previo de un modelo.
Evaluación de IA
Prueba reproducible que mide un comportamiento mediante casos, condiciones, métricas y una rúbrica explícita.
Generalización
Capacidad de mantener un comportamiento útil ante ejemplos o condiciones que no coinciden exactamente con los datos de entrenamiento.
Incertidumbre
Grado de falta de certeza sobre una predicción, una respuesta, la evidencia disponible o la validez de una medición.
LLM-as-a-judge: what it evaluates and which biases to check
An LLM-as-a-judge approach uses a language model to assess responses or actions against explicit criteria. This guide explains the process, distinguishes different types of judgment, and shows what to verify before relying on the results.
Reproducibilidad
Capacidad de repetir una evaluación con versiones, datos, configuración y procedimiento documentados y obtener resultados compatibles.
Robustez
Capacidad de mantener un comportamiento aceptable ante variaciones, ruido, casos extremos o intentos de manipulación.
Rúbrica de evaluación
Conjunto explícito de criterios y niveles que convierte una valoración en una puntuación interpretable y repetible.
Safety and governance
Risks, controls, and responsibilities throughout the lifecycle.
AI Hallucinations: What They Mean and How to Recognize an Unsupported Answer
A fluent answer is not necessarily a correct one. This guide explains what AI hallucination means, how to distinguish it from other errors, and what checks can help assess specific claims.
AI Guardrails: What They Control, Where They Act, and What They Don’t Guarantee
A guardrail is a control that checks a system’s inputs, outputs, or actions against a defined policy. Its scope depends on what it reviews and when it intervenes: it can reduce certain risks, but it cannot by itself prove that the entire system is safe.
Human-in-the-Loop (HITL): What a Person Decides—and What Their Involvement Does Not Guarantee
HITL describes a design in which a person intervenes at a defined point in an automated system. The label alone does not say what authority they have or guarantee that they will detect errors.
Instruction injection
Ataque o interferencia en la que contenido no confiable intenta desviar al sistema de sus reglas u objetivo legítimo.
Moderación
Clasificación y tratamiento de contenido según políticas de seguridad, uso aceptable o requisitos legales.
The Principle of Least Privilege: What It Means and How to Apply It to AI Systems
The principle of least privilege limits each identity—person, process, or service—to the permissions needed for its task. In AI systems, it guides access for agents, tools, and services, but does not replace authentication or, by itself, guarantee that a model behaves safely.
Adversarial Testing: Definition, Methodology, and Limits in AI Systems
Adversarial testing in AI is an intentional evaluation discipline that seeks to break a system's guarantees through hostile inputs or designed scenarios. This entry defines the concept, distinguishes manual practice from automation, details the technical lifecycle, and analyzes its inherent limits regarding coverage and reproducibility.
Supervisión humana
Capacidad efectiva de personas responsables para comprender, vigilar, intervenir y detener un sistema cuando sea necesario.
Verificación de hechos
Proceso de contrastar afirmaciones verificables con evidencia identificable, vigente y suficientemente autorizada.
Operations and infrastructure
Techniques for deploying, optimising, and observing AI systems in production.
Context Caching in AI: What It Reuses—and Why It Doesn’t Mean “Remembering”
A cache can preserve model computations so they do not have to be repeated. This guide distinguishes KV caching from prefix caching, explains when each can be reused, and clarifies their limits.
Quantization in AI: What Changes When Numerical Precision Is Reduced
Quantization represents numbers using fewer levels to reduce resource use, but “4-bit” alone is not enough to predict a model’s memory use, speed, or quality.
AI Inference: What Happens When a Model Processes an Input
Inference is the use of an already-trained model to calculate an output from an input. It can produce a class, score, representation, or generated content; it does not guarantee that the result is correct.
Latency in AI: What Time Is Measured and Why the Response Milestone Matters
Latency is the time between a defined start and a defined end. Learn to distinguish the first result, the complete response, and the time experienced by someone using an AI application.
Rendimiento de procesamiento
Cantidad de trabajo que un sistema completa por unidad de tiempo, por ejemplo solicitudes o tokens por segundo.
Try another word, an alias, or a different area.