Skip to the content
AI and Cybersecurity Learning and Practice Center Test automation Open the Learning Center

Glossary

LLM (large language model)

A model with a very large number of parameters, typically tens of billions, that reads and writes text. GPT, Claude, Gemini and Llama are families of them.

Everything in a model's context, from your instructions to an email it was asked to summarize, arrives as the same kind of text. That is why prompt injection works, and why what a model is allowed to do matters more than what it is told.

Open the glossary in the Learning Center