About
I'm Xabier Ariznabarreta. Born and raised in Madrid. I did high school at Trinity College in San Sebastián de los Reyes and now study AI Engineering at Universidad Francisco de Vitoria.
I started building AI projects at the beginning of my second year of the degree and shipped my first production agent a few months later. Since then I've sent several to production: commercial agents integrated with Salesforce, MCP servers with security-review loops, Android field assistants, multilingual institutional tooling.
The work was useful. It was also a teacher. The bugs were instructive, the customers were patient, and the experience showed me where the bottleneck is: not in the engineering, but in the science underneath.
So I'm pivoting to research. The first concrete step has been contributing to the open-source evaluation frameworks that safety organizations actually run. This site is the public notebook for the rest of it.
What you'll find here
Four kinds of posts:
- Deep dives: rigorous explanations of LLM concepts, transformer internals, mech interp, eval methodology.
- Research notes: evals, agent harnesses, and whatever I'm working through at the time.
- Production lessons: honest case studies from systems I've shipped, expensive mistakes included.
- Logbook: reflections on the builder-to-researcher pivot at 19.