Field notes for deploy-safety teams.

Practical writing on deploy risk, runbooks, incident response, dependency changes, and the habits that keep small engineering teams out of avoidable fire drills.

Written for

Lean engineering teams

Focus

Deploys, incidents, runbooks

Bias

Useful over theoretical

Latest writing

All inference llm localai verification

localai llm inference verification

Can You Tell When an LLM API Swaps in a Cheaper Model?

Providers have every reason to serve a smaller or more quantized model under load. I ran the experiment to see if you can catch it from the outside. The obvious method fails backwards, and the one that works needs to accumulate evidence.

Rob·Jun 16, 2026·4 min read