Building A Transformer To Predict Stocks


See part 1

Before we look at the model I still need to figure out why things are dying the moment we try to train - even on a simpler model. More process kills. This is undoubtedly due to memory again. The issue is that I don't really know if my …


LMM - Large Muffin Model


Last fall I was in the mood to bake and asked my wife what she wanted. Her response was simply "pumpkin". This was wholly unhelpful, but convenient since we happened to have pumpkin puree in the house. Without much forethought, I asked ChatGPT:

What is something simple I can bake …


Transformer Stock Prediction Part 1


I was listening to an episode of the Acquired Podcast where they were discussing Renaissance Technologies. They're a secretive hedge fund that uses machine learning (probably) to make a lot of money. At one point, the hosts hypothesized that RenTech discovered the underlying transformer architecture that powers modern large language …


An Introduction


A close friend convinced me to start this after she observed me bumbling around a project in an interesting way. So, that's what this will be. Generally bumbling around and documenting it.

A bit about me. I still consider myself a software engineer, though I do a lot less of …