New to AI? Start with Artificial Intelligence and Large Language Models, then see it all in action with our free guides and tools.
Plain-English definitions of the AI terms you keep running into — no jargon, with real examples and the free tools that put each idea to work.
An AI system that can take a goal and carry out multi-step actions to achieve it, not just answer a single question.
Read definition →A defined way for one piece of software to talk to another — how apps plug AI models and other services into their own products.
Read definition →Software that performs tasks we normally associate with human intelligence, like understanding language or recognizing images.
Read definition →A program you interact with through conversation — from simple scripted helpers to AI assistants powered by LLMs.
Read definition →The field of AI that lets computers interpret and understand images and video.
Read definition →The maximum amount of text an AI model can consider at once — its working memory for a conversation or document.
Read definition →A type of machine learning that uses neural networks with many layers — the approach behind most modern AI.
Read definition →The type of AI behind most modern image generators — it creates pictures by refining random noise step by step.
Read definition →A way of turning words, sentences or images into lists of numbers that capture their meaning so software can compare them.
Read definition →Taking an already-trained AI model and training it a bit more on specialized data to adapt it to a specific job.
Read definition →AI that creates new content — text, images, audio or code — rather than just classifying or predicting.
Read definition →The family of AI models, based on the transformer design, that powers many popular chatbots and writing tools.
Read definition →When an AI confidently produces information that is false, made up or not supported by its source.
Read definition →The "using" phase of AI — when a trained model takes your input and produces an output, like answering a prompt.
Read definition →A type of AI trained on huge amounts of text that can understand and generate human-like language.
Read definition →A way of building AI by letting software learn patterns from examples instead of being explicitly programmed with rules.
Read definition →The field of AI focused on getting computers to understand and work with human language.
Read definition →A model loosely inspired by the brain, made of layers of connected nodes that learn patterns from data.
Read definition →The instruction or question you give an AI to tell it what you want it to do.
Read definition →The practice of crafting and refining prompts to get better, more reliable results from an AI.
Read definition →A technique that lets an AI look up relevant information first, then use it to answer — reducing made-up facts.
Read definition →A setting that controls how random or predictable an AI language model’s output is.
Read definition →The small chunks of text — words or pieces of words — that a language model reads and generates.
Read definition →The examples an AI model learns from — its quality and range shape what the model can and cannot do.
Read definition →New to AI? Start with Artificial Intelligence and Large Language Models, then see it all in action with our free guides and tools.