Core concepts
LLM
Large Language Model — the type of AI behind tools like ChatGPT and Claude, trained to understand and generate text.
01 ——
In plain English
A Large Language Model (LLM) is an AI model trained on vast amounts of text — books, websites, code, and more — to predict and generate language. The "large" refers to the number of parameters (weights) inside the model, which can range from billions to trillions.
How they work (simplified):
- The model reads your input, broken into tokens
- It predicts the most likely next token, over and over
- The result is coherent, contextually relevant text
Well-known LLMs:
- GPT-4 / GPT-4o (OpenAI)
- Claude 3 / Claude 4 (Anthropic)
- Gemini (Google)
- Llama (Meta, open-source)
LLMs power most of the AI tools you see today — writing assistants, coding tools, customer support bots, and more.
02 ——
Related terms
Transformer
The neural network architecture introduced in 2017 that powers nearly every modern LLM, image generator, and AI breakthrough.
Foundation Model
A large, general-purpose AI model trained on broad data that can be adapted (via prompting or fine-tuning) to many downstream tasks.
Generative AI
AI systems that create new content — text, images, audio, video, or code — rather than just classifying or predicting from existing data.
GPT
Generative Pre-trained Transformer — the architecture behind OpenAI's models, and now used as shorthand for any LLM-powered chatbot.
Tokens
The basic units of text that AI models read and write — roughly ¾ of a word each. Models are priced and limited by token count.
Context Window
The maximum amount of text (tokens) an AI model can read and remember at once during a single conversation.
Back to glossaryLast reviewed May 2026