From 0.76 to 0.78: A 48-Hour Hackathon Journey in Data Science
How a 48-hour team sprint on the PISA math-score challenge moved from R² 0.76 to 0.78, and what hardware limits and CatBoost tuning taught us.
Archive Index // Search
Search the Wired
Every article, note, and topic in the archive.
No results match the selected topic.

Longer essays, build logs, and dispatches from the work.
All articlesHow a 48-hour team sprint on the PISA math-score challenge moved from R² 0.76 to 0.78, and what hardware limits and CatBoost tuning taught us.
A from-scratch account of training a GPT-2-scale language model: the architecture, data pipeline, compute constraints, and lessons from my first public project.