Learning AI

What I Learned Building and Training an LLM from Scratch (You Can Too)

In this post, I’ll share what surprised me most about building an LLM from scratch—where structure finally became visible. I wanted to write an autoregressive, transformer-based, decoder-only Large Language Model—like GPT, LLaMA, etc.—without too many abstractions and hand-holding. Andrej Karpathy, ARENA, Sebastian Raschka, Stanford's

Girish Gupta

Jan 13, 2026