Hey, I'm Pablo (or Pablin, if you're one of my people)
I'm currently trying to survive a master's in Computer Science applied to Artificial Intelligence, basically a huge nerd into Machine Learning, AI, quantized models, and stuff running on my own infra, mostly SLMs (screw big tech... nah, kidding, obviously I used uncle Claude and cousin Gemini to build this blog lmaooo). This blog is where I document what I'm studying (me and my models, local or not), metaphors and all, without ever dodging the real technical terms. The whole point here is getting you to walk away with something you can actually apply to your own project or your own studies, same thing I'm trying to do, honestly.
Latest posts
See all- Teaching a GPT From Scratch to Write Like a 19th-Century Brazilian Novelist
2026-08-23
Chapter 2 builds a tiny GPT from scratch, the same classic exercise from Karpathy's video. I clean-transcribe my entire notebook here, cell by cell, full code, comparing against the original notebook and finding real bugs along the way.
- SLM vs LLM: the Delivery Bike and the Moving Truck
2026-08-23
Chapter 1 of J. Paul Liu's book argues the giant model isn't always the right call. I tell it through the most Brazilian metaphor I know (a delivery bike vs a moving truck) and check the real cost numbers the book uses.
- Adaline: Train on the Line, Classify on the Sign
2026-08-20
Lectures 2e and 2f: the professor trains Adaline by fitting a continuous line to the ±1 labels (instead of fitting directly on the sign), and I connect this to the delta rule that already showed up in the other playlist. In the end, a deliberately biased dataset reveals the problem was never the training algorithm.
Timeline
See all
Getting shaken up by Go2026-08-19
Playlists
- Machine Learning Specialization (Andrew Ng)
My step-by-step notes going through Andrew Ng's Machine Learning Specialization (DeepLearning.AI / Stanford), course by course, lab by lab.
- Pattern Recognition
My notes from my Pattern Recognition course, lecture by lecture, with Bishop's book as the theoretical backbone.
- Neural Networks
My notes from my Neural Networks course, lecture by lecture, with Aggarwal's book as the theoretical backbone. A living playlist, growing along with the course.
- Papers
A diagonal read of articles and surveys I found cool, with no pretense of turning into a lecture. Simple code, a chart to give you a view, and the same conversation as always with you.
- Small Language Models
Chapter by chapter through "How to Build and Fine-Tune a Small Language Model", by J. Paul Liu. Why train your own model instead of outsourcing everything to an API, and how to build a GPT from scratch until it writes like a 19th-century Brazilian novelist.