Kevin Martin Jose

I’ve been thinking about binary neural networks lately, and specifically how to do it without computing full precision gradients.

When I was at Amazon’s LLM pre-training team, our pre-training jobs used to run for weeks.

Disclaimer: I do not know why PyTorch + MPS is faster (yet) I recently came across Apple’s MLX framework.

* Software as a Service ** serverless as in everything runs on AWS lambda.

Disclaimer: The post is more about understanding LUTs and HaldCLUTs and writing methods from scratch to apply these LUTs to an image rather than coming up with CLUTs themselves from scratch.

Disclaimer: All I’ve done is write a few config files.

TL;DR: Buy a kindle already.

A few years ago, very early into my programming career, I came across a story: The ceramics teacher announced on opening day that he was dividing the class into two groups.

Matchertools is my “hello world” project in rust, and I have been chipping away at it slowly and erratically for the past couple of months.

TL;DR: Learning to play the violin introduced me to western classical music, amateur orchestras, and deliberate practice.