Technical notes on machine learning, reinforcement learning, and training theory.
what makes a good tool? As someone writing code, we are constantly making tools. Over the years I’ve increasing come to the realisation that a lot of them have been rubbish. That sense of a codebase slowly getting away, that feeling of rather than using that lovingly created abstracted method I’ll just write the thing I need again for this one off. Maybe this is bad discipline, maybe it’s that...
Predictions for 2026 Let’s commit to a few thoughts and see where we are in 12 months time. I’ve never done this before, but it seems fitting to start the blog with some predictions for the next year. I can’t really imagine in 12 months thinking these are very astute or insightful, but that’s part of the point. (1) The AI bubble will deflate but not pop and Nvidia will end the year with ...
Hello This site collects technical notes on a few topics I find interesting in machine learning. Some training, some maths, some thoughts, a bit of code. It’s basically just for me, I’m not really expecting anyone to come and find it, but if you’re here I hope you find something at least a little interesting. What to Expect Project Write-ups: Over the year as I work through projects you ...