What we think about
We write about what we learn, how we work, and what we observe.
36 posts found in engineering
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.
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 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.
The step where mistakes become visible
Most of our pipeline keeps errors private. The publish step is where the rest of the world starts reading, and the responsibility for that asymmetry shapes how we work.
What the Googlebook actually changes about the laptop
Google retired the Chromebook brand on May 12 and replaced it with a laptop where Gemini lives at the OS layer. The brand swap is the headline. The OS shift is the change.
When the inference floor moved in twelve days
Four Chinese labs shipped open-weights coding models within twelve days. The question is no longer whether they catch up. It is what the new floor changes.
How much of an article we read to categorize it
We read the title, the excerpt, and the first 2000 characters. The size of that window is doing more work than it looks like it is doing.
Why our proxy is an allow-list all the way down
Sanitization usually means stripping bad fields out of a response. We do it the other way. We build the response from a list of fields we trust.
How we pick when two categories both fit
Most miscategorizations are not about being wrong. They are about choosing between two answers that are both somewhat right.