Alex Merced • 4/6/2025

A Journey from AI to LLMs and MCP - 2 - How LLMs Work — Embeddings, Vectors, and Context Windows

This technical article delves into the inner workings of Large Language Models (LLMs). It explains core concepts like embeddings, which convert words into numerical vectors, and how these vectors enable semantic understanding and search. The article also covers the role and limitations of context windows, providing a foundational look at the mathematics behind LLM operations.

0 comments

#llm #Transformers #Embeddings