The tail is the product
Why we throw away aggregate F1 on tagging benchmarks, and what we report instead. A short argument with a long table attached.
One category per kind of note: research arguments, data pipeline write-ups, infrastructure post-mortems and lab housekeeping.
2 posts
Why we throw away aggregate F1 on tagging benchmarks, and what we report instead. A short argument with a long table attached.
Inpainting treats a mask as damage. PrismStream treats it as composition. Notes from six weeks of getting that distinction to survive training.
1 post
On building Aurora: why every quality filter in the pipeline emits a column instead of deleting a row, and what that costs in storage.
1 post
Kubernetes answers a question small labs are not asking. Notes on writing a scheduler whose main feature is explaining itself.
1 post
The first post. Mostly here so the blog has something to render while the real writing gets started.