Loading…
Glossary term
A neural network trained on vast amounts of text to understand and generate language.
An LLM is a very large neural network, almost always a transformer, trained on vast amounts of text to predict the next token. Repeating that prediction produces fluent writing, code, summaries and answers.
After pretraining, models are usually tuned further so they follow instructions and behave helpfully and safely.
LLMs are the technology behind modern chat assistants and a large share of current AI news.