Artificial intelligence only needed attention

A legacy note about attention mechanisms, transformers, and why they changed the trajectory of natural language processing.

This is an editable English migration of a legacy article from the original blog. It keeps the central intent of the post while making it fit the newer research-oriented structure of the site.

A short note on PyTorch joining the Linux Foundation and what that means for open-source machine learning infrastructure.

Topics: Deep Learning, Python, Pytorch, Linux.

PyTorch joins the Linux Foundation

A concise introduction to deep learning, neural networks, and the kind of problems where layered models become useful.

What is deep learning?

Building a web development portfolio with Jamstack

A project note about building a web development portfolio with Jamstack ideas, React, Next.js, Tailwind, and deployable static workflows.

Topics: React, Next, Tailwind, Web Development, Jamstack.

A legacy note about PyScript, its promise, and the limits of thinking about Python in the browser as a direct JavaScript replacement.

Topics: Python, Javascript, Web-Development.

PyScript: a replacement for JavaScript?

Short notes on papers, technical decisions, experiments and questions that are still taking shape.

Notes close to research, papers, efficient systems and reproducible AI by Raul Pacheco Rodriguez.

Research notes - Raul Pacheco Rodriguez

Notes close to work in progress

Hardware-aware Pseudo-Softmax: a research note

This note organizes a hardware-aware view of approximating Softmax: the target is not only model accuracy, but an implementation that can be measured, verified, and mapped to efficient hardware.

The relevant questions are about approximation error, memory, parallelism, RTL constraints, and the impact of replacing an expensive operation inside a larger model.

A research note for organizing the intuition behind approximating Softmax when the goal is efficient and verifiable hardware.

Anti-leakage evaluation for reproducible medical AI

In medical AI, a strong number can hide a weak experimental question. This note frames anti-leakage evaluation as a prerequisite for reproducible and trustworthy systems.

The practical direction is to document data manifests, split data by the right real-world constraints, and report failure modes instead of only the best metric.

Initial notes on temporal shortcuts, information leakage, and more honest evaluation protocols for medical AI systems.

Why I am separating this research blog from FP32

This English version keeps the core idea of the original note: FP32 can remain a broader editorial space, while this site can host work that is closer to research, papers, systems, and professional updates.

The distinction matters because not every idea belongs in the same publication context. Some notes are exploratory, some are technical logs, and some are part of a longer academic trajectory.

A short note on why this site should host research-adjacent writing while FP32 remains an independent editorial lab.

A practical tutorial-style article about building a personal link hub with HTML and CSS instead of depending entirely on a third-party tool.

Build your own Linktree

A major year for generative AI: what comes next?

A legacy overview of the generative AI wave around 2022 and the questions it opened for creative tools, productivity, and technical education.

Topics: AI, Generative Adversarial Networks.

A legacy article about technology used in the 2022 Qatar World Cup and how data, sensors, and automation changed the game experience.

Technology at the 2022 Qatar World Cup

ChatGPT: OpenAI's powerful GPT-3-based chatbot

A legacy article explaining ChatGPT, its relationship with GPT-style language models, and why conversational AI became a useful interface for everyday users.

What Arduino is, what it is for, and where to get one

An introductory article about Arduino, physical computing, electronics learning, and how to start experimenting with boards and sensors.

A practical article about why React became a valuable tool for building user interfaces and learning frontend engineering.

Topics: React, JavaScript, Web Development.

Why learn React for web development?

A beginner-friendly introduction to artificial intelligence, its branches, examples, and why the field matters beyond hype.

What is artificial intelligence?

A beginner-friendly explanation of JavaScript's role in modern web development and how it connects interaction, tooling, and application logic.

JavaScript in web development

A compact tour of less obvious JavaScript use cases beyond simple websites, including tooling, apps, and creative development.

Lesser-known uses of JavaScript

A broad tour of what JavaScript can be used for, from web interfaces to servers, tooling, and creative experiments.

What can you build with JavaScript?

Why should JavaScript be my first language?

A beginner-oriented argument for starting with JavaScript because it connects quickly with visible, interactive projects on the web.

A project note about recreating the Google search homepage as a practical exercise in HTML, CSS, layout, and attention to interface detail.