Interactive AI Learning

Master AI Concepts
Through Experience

Explore artificial intelligence and large language models through beautiful, interactive demonstrations. Learn by doing, not just reading.

Start Learning Browse Topics

LMF Blog

Latest AI news, model analysis, and deep dives

Interactive Demos

Hands-on explorations that make abstract concepts tangible and intuitive.

Visual Learning

Beautiful visualizations that reveal how AI systems actually work under the hood.

Build Intuition

Go beyond memorization—develop deep understanding through experimentation.

Help Make This Better

This guide is open source. Got an idea for a new topic? Found a bug? Want to improve an explanation? Every contribution helps.

Request a Topic Report a Bug Star on GitHub

Explore Topics

Dive into interactive lessons

Artificial Intelligence

Getting StartedMake your first LLM API call in 10 minutes — for freeFeb 10, 2026

AI Agents

Core Concepts

The Agent LoopThe observe-think-act cycle that powers autonomous agentsJan 24, 2026

Context AnatomyHow agents structure and manage their context windowJan 24, 2026

Building Blocks

Tool DesignPrinciples for building tools that agents can use reliablyJan 24, 2026

Programmatic Tool CallingLet agents write code that calls tools, reducing latency and tokensFeb 23, 2026

Memory SystemsHow agents remember across conversations and sessionsJan 29, 2026

Agent SkillsReusable capabilities that extend what agents can doJan 29, 2026

MCP (Model Context Protocol)A standard protocol for connecting agents to external toolsJan 29, 2026

Patterns

Agentic PatternsArchitectural patterns like ReAct, reflection, and multi-agentJan 24, 2026

OrchestrationCoordinating multiple agents and tools for complex tasksJan 29, 2026

Quality & Security

Agent ProblemsCommon failure modes: loops, hallucinations, and goal driftJan 24, 2026

Agent SecurityDefending agents against prompt injection and data exfiltrationJan 29, 2026

EvaluationMeasuring agent performance with benchmarks and metricsJan 29, 2026

Large Language Models

Fundamentals

TokenizationHow text gets broken into pieces the model understandsJan 24, 2026

EmbeddingsTurning words into numbers that capture meaningJan 29, 2026

Attention MechanismHow transformers decide which tokens matter for each predictionJan 31, 2026

Behavior

TemperatureControl randomness and creativity in LLM outputsJan 24, 2026

Context RotWhy models forget instructions in long conversationsJan 29, 2026

Capabilities

RAGAugment LLM answers with retrieved external knowledgeJan 31, 2026

Vision & ImagesHow LLMs process and understand images alongside textJan 24, 2026

Visual ChallengesWhere vision models fail: counting, spatial reasoning, OCRJan 29, 2026

Agentic VisionActive visual investigation through zoom, crop, and code executionJan 29, 2026

MultimodalityProcessing text, images, audio, and video in one modelFeb 1, 2026

Architecture

Transformer ArchitectureThe foundational architecture behind GPT, BERT, and all modern LLMsFeb 9, 2026

LLM TrainingFrom pretraining on raw text to fine-tuning with human feedbackJan 29, 2026

Training DataWhere AI models get their knowledge: legitimate sources, controversies, and synthetic dataFeb 24, 2026

Mixture of ExpertsRun only a fraction of model parameters per tokenJan 31, 2026

QuantizationShrink model size by reducing numerical precisionJan 31, 2026

Nested LearningLearning algorithms that operate at multiple levelsFeb 8, 2026

DistillationTransfer knowledge from a large model to a smaller oneFeb 5, 2026

Fine-Tuning & LoRAAdapt large models efficiently by training only tiny low-rank matricesFeb 9, 2026

Speculative DecodingSpeed up inference by drafting tokens with a smaller modelFeb 5, 2026

Diffusion Models

How Diffusion WorksForward noise, reverse denoising, and why score estimation worksFeb 25, 2026

Text DiffusionMask-and-predict generation with fixed-length token gridsFeb 25, 2026

Image DiffusionLatent denoising pipelines behind modern text-to-image systemsFeb 25, 2026

KV CacheStore computed keys and values to avoid redundant workFeb 9, 2026

Prompt CachingReuse computed KV caches across API requests to save cost and latencyFeb 19, 2026

Batching & ThroughputProcess multiple requests simultaneously for higher throughputFeb 9, 2026

Running Models LocallyRun LLMs on your own hardware for privacy, speed, and zero API costsFeb 9, 2026

VRAM CalculatorEstimate VRAM requirements and inference speed for running local LLMsFeb 27, 2026

Neural NetworksLayers of connected neurons that learn patterns from dataJan 24, 2026

Gradient DescentThe optimization algorithm that trains neural networksJan 29, 2026

Training ProcessHow models learn from data through forward and backward passesJan 24, 2026

World ModelsInternal simulators that let AI predict and plan in virtual worldsFeb 15, 2026

Prompting

Prompt BasicsFundamental techniques for getting good results from LLMsJan 24, 2026

Advanced TechniquesChain-of-thought, few-shot, and other power techniquesJan 29, 2026

System PromptsSet the persona, rules, and behavior of an LLMJan 29, 2026

AI Safety & Ethics

Bias & FairnessHow training data biases surface in model outputsJan 24, 2026

Responsible AIBuilding AI systems that are fair, transparent, and safeJan 29, 2026

AI Industry

AI Made in EuropeThe growing European AI ecosystem and its unique strengthsJan 24, 2026

Open Source AdvantagesWhy open weights matter for innovation and transparencyJan 29, 2026

Logge's Favourite ModelsCurated picks of the best models for different tasksFeb 9, 2026

LLM Tier ListA subjective ranking of current LLM models by quality and use case fitFeb 19, 2026

Pro tip: PressCtrl+Kto search topics