AI glossary
The words that come up every time people talk about AI, explained plainly and with an example. Start with token and LLM: with those two, almost everything else makes sense.
- AI agent
- An AI agent is a system where a model does more than answer: it decides on steps, uses tools and acts in a loop until it reaches a goal.
- Artificial intelligence (AI)
- Artificial intelligence is the field that gets computers to do tasks we associate with human intelligence: understanding language, seeing, deciding or creating.
- Context window
- The context window is the maximum number of tokens a model can take into account at once: your message, the conversation, any documents and its own answer.
- Embeddings
- An embedding is a list of numbers that represents the meaning of a text or an image. Texts with similar meaning end up close to each other.
- Fine-tuning
- Fine-tuning means further training an already trained model on a small set of your own examples, to specialize it in a task, a style or a format.
- Generative AI
- Generative AI is AI that creates new content (text, images, audio, video or code) based on what it learned from huge numbers of examples.
- Hallucination
- A hallucination is when an AI model generates false or made-up information and presents it with full confidence, as if it were a real fact.
- LLM (large language model)
- An LLM (large language model) is an AI model trained on huge amounts of text to predict the next token. It is the engine behind ChatGPT, Claude and Gemini.
- Machine learning
- Machine learning is the branch of AI where a system learns patterns from examples instead of following rules someone programmed by hand.
- MCP (Model Context Protocol)
- MCP is an open protocol for connecting AI models to external tools and data, so that a single integration works across many applications.
- Neural network
- A neural network is a model made of layers of simple connected units, with weights that are adjusted during training. It is the basis of deep learning and of LLMs.
- Prompt
- A prompt is the instruction or text you give an AI model so it responds. The clearer the context and the goal, the better the answer tends to be.
- RAG (retrieval-augmented generation)
- RAG is a technique that finds relevant information in your documents and hands it to the model along with the question, so it answers with real, current data.
- Temperature
- Temperature is a setting that controls how much randomness a model uses when picking the next token: low gives more predictable answers, high gives more varied ones.
- Token
- A token is the small chunk of text a language model works with: a word, part of a word or a symbol. Context length and cost are both measured in tokens.
- Transformer
- The transformer is the neural network architecture behind almost every current LLM. Its key piece, attention, relates each token to all the others.
Updated on