LLM (Large Language Model)
AI & Emerging Tech
An AI model trained on vast amounts of text to understand and generate language.
In practice
A large language model is a neural network trained to predict text, which at sufficient scale turns into something that can summarise, translate, reason through problems, write code and hold a conversation. Claude, GPT and Gemini are LLMs. For a designer, it is the engine behind most of what is currently called AI in software — and its habits, including confident mistakes, shape what you can build on it.
Questions
What is LLM (Large Language Model)?
An LLM is a very large model trained on text that can read, write and reason in natural language well enough to do useful work.
Why do you use LLM (Large Language Model)?
It is the general-purpose component that made conversational, generative and agentic products possible without building a bespoke model for each.
How do you use/apply LLM (Large Language Model)?
You send it text — a prompt, plus any context or tools — and it returns text. Everything from a chatbot to an agent is built by shaping what goes in and what happens to what comes out.
When do you use LLM (Large Language Model)?
Whenever a task involves understanding or producing language, and precision can be checked. Be careful where a fluent wrong answer is worse than none.
Who uses LLM (Large Language Model)?
Everyone building software now, and the designers deciding what those products should feel like.
