Posts by Year

2026

Cross Entropy Loss Connection to GPT Models

  1 min read

Cross-entropy loss isn’t a heuristic, it is maximum likelihood estimation with a sign flip. It also shows how the same math powers GPT training.

Back to Top ↑

2025

Back to Top ↑

2023

Back to Top ↑

2020

Back to Top ↑

2019

Banco Data Model

  1 min read

this line will show up as preview on the posts page

First Post

  1 min read

import sys a = [1,2,3] print(a)

Back to Top ↑