Explained
Every term on this page is explained the way you'd tell a sharp friend — the library grows with every WTF-is-X episode.
Fine-tuning takes a trained model and gives it a short second education on your own examples — your tone, your formats, your field — so the behaviour sticks without teaching anything from scratch. Think of hiring a brilliant generalist, then spending a week training them on your house style.
The context window is the model's working memory — how much text it can hold in mind at once, counting your question, the conversation so far, and anything you pasted in. When it fills up, the oldest material falls out, which is why very long chats start to drift. Bigger windows exist; they cost more to run.
Go deeper →A model's knowledge is stored as billions of numbers. Quantization rounds those numbers to a coarser precision — like compressing a photo — so the model takes far less memory and runs faster and cheaper. Done carefully, the quality loss is barely measurable, which is why almost every model you use is quantized.
Go deeper →Training builds the model; inference is using it. Every time you ask a chatbot a question, a data centre runs your words through the model and generates the reply, one word-piece at a time. Training happens once — inference happens billions of times a day, and every run costs money.
Read the full explainer →Go deeper →Instead of hoping the model memorised the right facts, you hand it the right documents at question time. The system searches your files, pastes the best passages into the prompt, and the model answers from those. It is why a chatbot can cite your company wiki without being retrained on it.
Read the full explainer →A chatbot answers you; an agent acts for you. Give it a goal and it runs a loop — pick a step, use a tool like search or code, check the result, adjust, repeat until the job is done. The bet is delegation: you review finished work instead of doing the work yourself.
Go deeper →Evals are the test suite for an AI system: a fixed set of questions with known good answers, scored automatically every time something changes. Without them, you are guessing whether a new model or prompt actually made things better. Teams with sharp evals ship improvements; teams without them ship vibes.
Go deeper →Not every question needs the biggest, most expensive model. A router reads each request and sends easy ones to a small, cheap model and hard ones to the heavyweight. Users rarely notice the difference — the bill notices, which is why most serious AI products quietly do this.