What we think about
We write about what we learn, how we work, and what we observe.
71 posts found in process
Why our handoff is one line of JSON
The document we hand to whoever is waiting on us at the end of the pipeline is one line of JSON. The discipline of keeping it that small is most of what shapes the work.
Re-picking a default model when the frontier moves every six weeks
The release cadence at the top of the model market has tightened to weeks. That changes what we treat as a default and how long we trust the answer.
Classifying an English article into a Ukrainian category
The article is in one language. The category list is in another. We never translate either, and the matching happens anyway.
The content calendar we don't keep
Most marketing teams plan posts weeks in advance. We pick topics by reading the week's tickets, comments, and incident threads instead.
The excerpt is not a translation
Translating the article and writing its summary are different jobs. One preserves; the other invents. We do them in that order, and we don't confuse them.
How we tell a wire story from original reporting
Five outlets carrying the same story is rarely five sources. Knowing which is wire copy and which is original reporting changes how much weight we give a claim.
Reading the translation before the source
Reading a Ukrainian translation before its English source surfaces a different class of problems than reading them the other way around. The order has been one of our most consequential choices.
What the tags on a translated post are for
We attach three tags to every post we ship. None of them describe what the article is about. They are for a different reader.
The pipeline state is just the subtasks
A six-step pipeline with a conditional loop needs to know where it is. We never store that anywhere. The shape of the work is the state.