How AI Large Language Models work: Explained in simple English

LLM (Large Language Models) are considered to be the foundation for text-based generative AI. These models, such as the GPT model of ChatGPT, are designed to generate human-like text based on the input they receive. In the large scheme of things, LLMs are the models that are trained to predict the next word when they generate textual output.

This article by Tim Lee on Ars Technica explains in simple terms about word vectors, transformers, and how the language models are trained.