Learn
AI Concepts184
Plain-English explanations of the terms you keep encountering in the news.
Learn
Data Drift
The gradual or sudden shift in the statistical properties of data that a deployed ML model receives compared to the data it was trained on - the most common cause of silent model degradation in production.
Read the full explanation →
Analogy
A weather forecasting model trained on historical climate data for a specific region. If the climate itself changes - warmer average temperatures, more intense precipitation events, shifting seasonal patterns - the model's predictions become increasingly unreliable not because the model is wrong but because the world it was trained to describe has changed. Data drift is this same problem applied to any ML model: the underlying reality it was trained on is no longer the reality it is operating in.
New to AI?
Follow the learning path - 10 sections from first principles to advanced topics, in the right order.
Browse by section
AI Foundations
The basics before anything else - what AI and machine learning actually are, how neural networks learn, and the building blocks every other concept assumes you know.
LLM Architectures
The building blocks inside large language models - how they store knowledge, process text, and generate responses.
Training & Alignment
How models are built, fine-tuned, and taught to behave the way people actually want them to.
Generative & Multimodal
AI that creates images, audio, and video - and systems that reason across multiple types of input at once.
Agentic AI
AI that plans, acts, and uses tools autonomously - moving beyond question-and-answer into doing.
AI Safety & Alignment
The field dedicated to making AI systems behave reliably, honestly, and without causing unintended harm.
MLOps & Infrastructure
The engineering discipline of running AI in production - reliably, efficiently, and at scale.
Reinforcement Learning & Robotics
AI that learns by doing - and the systems that let it operate in the physical world.
Graph Neural Networks
A class of models built for data with relationships - social networks, molecules, maps, and knowledge graphs.
Specialized Domains
AI applied to medicine, science, audio, and other fields where domain knowledge changes everything.