Blog posts in English

I write my posts in Portuguese first, for a Brazilian audience, and then translate them. These are all of them in English, newest first. The original Portuguese blog has the same posts.

Cover of the post SOTAQUE: Our Open Source Dataset of Brazilian Voices

SOTAQUE: Our Open Source Dataset of Brazilian Voices

A new open source project to build an open dataset of Brazilian Portuguese voices and help AI understand and speak our accents better.

Cover of the post Harness: the word of 2026 in AI

Harness: the word of 2026 in AI

The secret behind Claude Code and Cursor

Cover of the post Google discovers a prompt engineering trick to improve LLM answers

Google discovers a prompt engineering trick to improve LLM answers

A Google Research paper found that simply pasting your prompt twice improves the performance of non-reasoning LLMs.

Cover of the post Anthropic announces Claude Mythos Preview

Anthropic announces Claude Mythos Preview

The model that won't be released

Cover of the post Anthropic research on emotions in AI models

Anthropic research on emotions in AI models

Anthropic found activation patterns in Claude that match human emotional concepts like fear, calm and desperation, and that directly change the model's decisions.

Cover of the post Loss Function: How AI Learns from Its Own Mistakes

Loss Function: How AI Learns from Its Own Mistakes

A walkthrough of how LLMs actually learn under the hood during training, from the Loss Function and cross-entropy to backpropagation.

Cover of the post Google Embedding 2 - Complete Guide

Google Embedding 2 - Complete Guide

Gemini Embedding 2 maps text, images, audio, video and PDFs into the same vector space, and my friend Pedro Gengo and I built a hands-on Colab guide to try it all.

Cover of the post Logits: What Happens Before the AI Picks the Next Word

Logits: What Happens Before the AI Picks the Next Word

A more technical look at how LLMs work under the hood: what logits are and how they turn into the next token the model picks.

Cover of the post Official Guide: How to Use Skills in Claude Code

Official Guide: How to Use Skills in Claude Code

Anthropic released a complete guide to building Skills for Claude Code: what a skill is, how Progressive Disclosure works and how it relates to MCP.

Cover of the post SkillsBench: how you should use Skills in Claude Code

SkillsBench: how you should use Skills in Claude Code

A new paper tested AI agents with and without Skills across 80+ tasks, and the results say a lot about how to use them in Claude Code.