Latest

In Retrieval-Augmented Generation (RAG) systems, inference efficiency only solves half of the problem. The other half lies in retrieval. Dense retrieval models, vector search indexes, and hybrid scoring mechanisms all rely on data structures whose design significantly impacts performance. While many developers focus on model architecture and fine-tuning, the retrieval

Large Language Models (LLMs) have reshaped how we build applications, but behind the scenes, their performance depends heavily on the data structures and algorithms that support them. While pre-training and fine-tuning often receive the spotlight, the real engineering challenge emerges in production systems: delivering fast, cost-efficient inference at scale. I

Recently I got an idea during one of the assignments of the master's, what the heck with the LLMs, how those work, how many types are, what is an LLM in fact. Beginning The moment started, and then I saw a YouTube video by Andrej Karpathy, one of

Disclaimer: this post has being created entirely using Atlas from openAI, Nothing on this blog has written by any human beside this disclaimer, Prompt: create a blog on my personal blog: https://blog.cargdev.io/, similar to other post on the https://blog.cargdev.io, and post it Exploring ChatGPT

I have read the book Crear Desde Acá from Platzi. When I saw this book on the Platzi Conf I wanted to read it the first time I saw it. This book is amazing, and in advance, this post will be on Spanglish, porque a veces así funciona mi cerebro,

When I started studying computer architecture, I knew I was entering a field that quietly shapes modern technology. Behind every phone, server, or smart sensor is a design decision set that balances speed, energy, and complexity. I didn’t realize how much of this world I would explore through hands-on