AI glossary

What Is Multimodal AI? A Plain-Language ExplanationMultimodal AI is a single model that can take in and work with more than one kind of data at once — text, images,… What Is Fine-tuning? A Plain-Language ExplanationFine-tuning means taking a model that has already been trained and training it a bit further on your own targeted examples, so it fits… What Is AI Hallucination? A Plain-Language ExplanationAI hallucination is when a language model produces fluent, confident text that is factually wrong or entirely invented. The term is worth knowing because… What Is a Token? A Plain-Language ExplanationA token is the smallest unit of text a language model works with: it might be a whole word, part of a word, or… What Is a Context Window? A Plain-Language ExplanationA context window is the total amount of text a model can hold in a single request, counted in tokens, with your input and… What Is a Large Language Model (LLM)? A Plain-Language ExplanationA large language model (LLM) is an AI model trained on huge amounts of text that generates language by predicting the next word. You… What Is Chain-of-Thought? A Plain-Language ExplanationChain-of-Thought is a prompting method that asks a model to write out its intermediate reasoning steps before it commits to a final answer. It… What Is Text-to-Image? A Plain-Language ExplanationText-to-image is a technique where you type a description in plain words and the AI generates a matching picture. Write "an empty beach at… What Is Voice Cloning? A Plain-Language ExplanationVoice cloning takes a recording of a target voice, trains a model on it, and then reads any text you type back in that… What Is a System Prompt? A Plain-Language ExplanationA system prompt is a fixed set of instructions you give an AI before the conversation starts, setting its role, tone, and limits. It…