AI concepts, one analogy at a time
From tokens to transformers. Every hard AI term explained with one everyday analogy, with a hands-on tool to try right after.
Categories
Full index →AI Basics
Artificial intelligence, machine learning, deep learning, model, training, inference: the words that show up first in any AI topic. If AI news feels foreign, start with the beginner terms here. Every other category builds on this one.
41 termsLanguage Models
How chat AIs like ChatGPT read and write. Tokens, transformers, attention, embeddings, prompts, hallucinations, RAG, context windows: the words you have probably met while using AI.
73 termsGenerative AI
How AI makes images, video and music, and how to use it. Diffusion, GANs, prompt engineering, negative prompts, seeds, upscaling: the terms you meet the moment you open an image generator.
47 termsVision & Audio
How AI recognizes objects in photos, tracks body poses and turns speech into text. CNNs, object detection, segmentation, pose estimation, TTS, STT: many of these you can try with just a webcam and a microphone.
47 termsTraining Methods
How AI learns from data. Supervised, unsupervised and reinforcement learning, fine-tuning, overfitting, loss functions, gradient descent: the steps hidden behind the word "training", one at a time.
58 termsNetwork Architecture
What the inside of an AI model looks like. Neurons, layers, weights, activation functions, RNNs, LSTMs, parameters: what people actually mean when they say a model is "big" or "deep".
62 termsEvaluation & Data
How we measure whether AI is any good, and what data we teach it with. Accuracy, precision and recall, benchmarks, labeling, bias, data augmentation: the words you need to read a results table.
42 termsEthics & Safety
What to watch out for when using AI. Bias, deepfakes, prompt injection, alignment, copyright, privacy: concepts that are all over the news yet hard to pin down.
38 termsTools & Usage
The terms you meet when actually using and connecting AI. Agents, APIs, open-source models, running locally, multimodal, plugins: what you need to know to pick and combine AI services.
48 termsFew-Shot Learning
Showing a couple of worked examples and asking for the same
Pick up a gym machine for the first time and a trainer rarely explains at length.
Read the analogy →How about these?
Grouping similar things together with no labels at all
Human in the LoopPutting a person's judgment at key points in an AI workflow
BackpropagationTracing error backward to split blame across the network
Open WeightsA model that hands out only the finished trained numbers
Instruction TuningTeaching a model to answer in the shape a request calls for
Popular terms
A system that picks out what you'll like from your past records
Large Language ModelA language model grown enormous by reading a huge pile of text
TransformerAn AI design where every word in a sentence looks at all the others
VRAMThe workspace where a graphics card lays out its numbers to compute
OverfittingMemorizing the practice answers and failing on anything new