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 Embeddings: The Map That Teaches AI to Understand the World

Embeddings: The Map That Teaches AI to Understand the World

Embeddings turn text, images and audio into lists of numbers that form a map of meaning. Here is how they work, how LLMs learn them, and why they power RAG.

Cover of the post The Claude Fable 5 shutdown, AI sovereignty and national security

The Claude Fable 5 shutdown, AI sovereignty and national security

After the US government cut off Claude Fable 5 for non-Americans overnight, what does that mean for countries running critical infrastructure on third-party models via API?

Cover of the post Claude Fable and Claude Mythos: everything you need to know

Claude Fable and Claude Mythos: everything you need to know

Anthropic finally released Claude Mythos 5 and Claude Fable 5. I got to see the dragon, but through glass, with warning labels and a few asterisks.

Cover of the post Einstein, Douglas Adams, Arrival, and Scientific AI

Einstein, Douglas Adams, Arrival, and Scientific AI

Lately, my reading on the subway and before bed has been “Story of Your Life”, the Ted Chiang short story that inspired “Arrival”, one of my favorite movies because it brings together science fiction, linguistics, and communication between different species.

Cover of the post Anthropic says HTML is better than Markdown for AI outputs

Anthropic says HTML is better than Markdown for AI outputs

A post by a Claude Code engineer made a lot of noise in recent weeks

Cover of the post RecursiveMAS: AI agents communicating by telepathy

RecursiveMAS: AI agents communicating by telepathy

A new paper from Stanford, MIT and NVIDIA proposes that multi-agent systems stop trading walls of text and start communicating directly in the models' latent space.

Cover of the post Harness: the word of 2026 (and how Codex works under the hood)

Harness: the word of 2026 (and how Codex works under the hood)

Why Codex and Claude Code do so much more than the same model in a chat window: what a harness is, and what I found by reading Codex's open source code.

Cover of the post TUTORIAL: A guide to quantizing Hugging Face AI models to GGUF and running them with Ollama

TUTORIAL: A guide to quantizing Hugging Face AI models to GGUF and running them with Ollama

How to shrink an open source Hugging Face model with quantization, convert it to GGUF with llama.cpp, and run it on your own laptop or phone with Ollama.

Cover of the post With AI, I became a hostage of my own ideas

With AI, I became a hostage of my own ideas

When every idea seems doable, the hard part stops being execution. It becomes knowing when to stop.

Cover of the post Claude Code, Doubled!

Claude Code, Doubled!

Anthropic teams up with SpaceX