My ramblings
This is mostly about the things that I am learning and don't want to forget just yet!
Converting a Rust Vector into an Iterator
A lot of teams building on top of LLMs ship a prompt, look at a handful of outputs, decide it "seems good," and move on. That works right up until a model update, a prompt tweak, or an edge case quietly breaks something nobody's testing for. Evals are the fix — the same instinct that gives you unit tests and regression tests for regular code, applied to something that doesn't produce the same output twice.
Once you've got Node Exporter reporting host-level metrics, the next question is usually: what should I actually put on a dashboard for my services? The RED method is one of the simplest, most reusable answers to that question.