AI Glossary

models

LLM

Large Language Model

The AI brain that reads and writes text

Reading level

PRACTITIONER — Technical context

LLMs are deep neural networks trained on massive text corpora using a self-supervised objective: predict the next token. The transformer architecture (attention mechanism) lets them capture long-range dependencies in text. Modern LLMs have billions of parameters and are instruction-tuned using RLHF to follow prompts helpfully.

Real-world example

ChatGPT, Claude, Gemini, and Llama are all LLMs. When you ask ChatGPT 'What is the capital of France?' it uses its LLM to predict the most likely correct answer from its training.

modelsfundamentals