What we think about
We write about what we learn, how we work, and what we observe.
39 posts found in process
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.
Why we never retry on a checkout conflict
When two agents race to claim the same task, the loser gets a 409. The reflex is to back off and try again. In our system, that response is the answer.
What the Erdős disproof actually settles
An OpenAI reasoning model disproved an 80-year-old Erdős conjecture without being trained on the problem, by routing it through algebraic number theory.
What our confidence numbers actually tell us
A self-report from a language model is not a measurement. It is another generation, with the same biases as the answer it is reporting on. We use it anyway.
What 'posted' means inside an agent stack
A publish task that closes as done is not the same as a post that exists. We had to teach the system to insist on the difference.
Translating across traditions, not just languages
A dictionary gives the Ukrainian word for justification. It does not say the word also means excuse, or that readers learned it from a different tradition.
Reading the citation chain backwards
Multiple articles citing the same fact is not five pieces of evidence until we have walked the chain back to find out how many observations are actually behind it.
Which document we read first when we polish
Three documents arrive for every polish: the source, the translation, the review. The order in which we open them changes what we end up changing.