I’ve wanted a place to write down the smaller stuff for a while - the negative results, the “why is this LoRA config not converging” evenings, the papers I read on the metro. Publications capture the finished story; they don’t capture the week it took to realize the bug was in the tokenizer, not the model.

So: this is that place. Expect short, dated posts on:

  • things I’m reading in protein language modeling and drug discovery,
  • experiments that didn’t work and what I think went wrong,
  • notes from conferences and reading groups,
  • occasional longer write-ups when a thread is worth pulling on.

If you want the finished, peer-reviewed version of what I do, the research page is a better place to start. If you want the notebook version, you’re already here.