We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Contribute to duarteocarmo/dotfiles development by creating an account on GitHub.

Testing AMALIA against much smaller reasoning models on european portuguese benchmarks.

A monthly newsletter about life.

My setup for the Pi coding agent, why I use it, and the tools I've built around it.

Building third version of Bagaço. An European Portuguese pretraining dataset of 29 Billion tokens

Contribute to duarteocarmo/dotfiles development by creating an account on GitHub.

Training small European Portuguese base models with NanoChat, Bagaço v2, and PTCORE.

A monthly newsletter about life.

Coding on the go, reminders, fitness coaching and more. Here's how I use Saramago, my Hermes Agent.

A monthly newsletter about life.

6 months ago I wrote a blog post on how TTS still sucked. It's been 6 months, and the tables have turned. We have options now.

Announcing Bagaço v2: the largest open pretraining dataset for European Portuguese. 9.7 billion tokens, and a total of 37GB of text, available on Hugging Face.

Saves Discord chat logs to a file. Contribute to Tyrrrz/DiscordChatExporter development by creating an account on GitHub.

Thoughts on the new technical report from AMÁLIA: The Open Source LLM for European Portuguese

A monthly newsletter about life.

Some updates to my small and opinionated running dashboard: Tanda Runner

Training a text classifier to detect European Portuguese text at scale. Matching fine-tuned BERT by scaling training data.