The map of AI — every concept, connected | Artifipedia

Skip to content

GlossaryMapBlog

Fields

Navigate

The map of AI.

Every concept on Artifipedia, and every link between them. Drag a node, hover to trace its connections, click to read.

Deep LearningLanguage & LLMsAI AgentsGenerative AIMachine LearningComputer VisionSafety & EthicsFoundationsTools & Ecosystemdrag · hover · click to open

Embed this map

Embed the map

Free to use on any site. Paste this where you want it to appear — it stays current as the encyclopedia grows.

Size<br>StandardTallCompact

Embed code

Copy codeClose

56 concepts · 150 connections · this map is generated from the "connects to" links on every entry, so it grows as the encyclopedia does.

Every concept<br>Agent Memory<br>Giving an AI a way to remember across conversations, since the model itself forgets everything the moment a session ends.<br>AGI (Artificial General Intelligence)<br>A hypothetical system with broad human-level capability across domains — undefined enough that people can argue about whether it's arrived.<br>AI Agent<br>Software that pursues a goal by taking its own steps — deciding, acting, and reacting — instead of answering once and stopping.<br>AI Alignment<br>The problem of making AI systems actually do what people intend — reliably pursuing the goals we want, not just the ones we accidentally specified.<br>Artificial Intelligence<br>The field of making machines do things that seem to require intelligence — a definition that has moved every time the machines succeed.<br>Attention<br>The mechanism that lets an AI decide which other words matter when interpreting each word — the core idea behind transformers.<br>Backpropagation<br>The algorithm that works out which weights caused a mistake and by how much — the reason neural networks can learn at all.<br>Bias & Fairness<br>The problem of AI systems producing unfair or discriminatory outcomes — usually by absorbing biases present in their training data.<br>Chain-of-Thought<br>Getting a model to reason step by step before answering — which dramatically improves its performance on hard problems.<br>Clustering<br>Grouping things that resemble each other — and the fact that the algorithm always returns groups, whether or not any exist.<br>CNN (Convolutional Neural Network)<br>A network that slides small filters across an image to find local patterns — the architecture that made computer vision work.<br>Context Window<br>The maximum amount of text an AI can consider at once — its short-term working memory, measured in tokens.<br>Deep Learning<br>Machine learning using neural networks with many layers — the approach behind nearly every recent AI breakthrough.<br>Diffusion Model<br>How most AI image tools work — starting from random noise and removing it step by step, guided by a prompt, until a picture appears.<br>Embeddings<br>Turning words (or images, or anything) into lists of numbers, arranged so that similar meanings end up close together.<br>Explainability<br>Getting a model to show its working — and the uncomfortable fact that most methods explain the explanation, not the decision.<br>Feature Engineering<br>Reshaping raw data into things a model can actually use — still where most of the accuracy comes from outside deep learning.<br>Fine-tuning<br>Continuing a model's training on your own examples so its behavior changes — baked into the model, not supplied at answer time.<br>GAN (Generative Adversarial Network)<br>Two networks trained against each other — one faking, one detecting — until the fakes pass. The technique diffusion largely replaced.<br>GPU<br>The chip that made deep learning possible — thousands of small cores doing the same maths at once, which is exactly what neural networks need.<br>Gradient Descent<br>Walking downhill on the error surface, one small step at a time — how a model's weights actually get updated.<br>Guardrails<br>The checks around a model that decide what it's allowed to receive, say, and do — the part that stops a demo becoming an incident.<br>Hallucination<br>When an AI produces something fluent and confident that is simply false — fluency is not the same as accuracy.<br>Image Classification<br>Getting an AI to look at an image and say what it is — the foundational task of computer vision.<br>Image Segmentation<br>Labelling every pixel rather than drawing a box — what you need when the exact shape matters.<br>Inference API<br>Renting a model by the request — how nearly everyone actually uses AI, and the dependency that comes with it.<br>Intelligence<br>The word underneath "artificial intelligence" — used constantly, defined by nobody, and the reason the field's biggest arguments never resolve.<br>Jailbreaking<br>Getting a model to do what it was trained to refuse — and the structural reason it keeps working.<br>Large Language Model (LLM)<br>An AI trained on enormous amounts of text to predict the next piece of writing — the technology behind chatbots like ChatGPT and Claude.<br>Loss Function<br>The number that says how wrong the model is — and therefore the definition of what it's trying to become.<br>Machine Learning<br>Getting computers to learn...