The escalation trap
Routing cheap-first and retrying on a bigger model when the answer looks bad, which usually costs more than routing correctly up front.
By Lattice editorial · Entry last reviewed · method
What it implies
Three reasons it fails: the cheap model cannot judge its own output, failures cluster on hard cases so escalation doubles cost precisely where it was needed, and one provider hiccup away from a retry storm. It only works when a failure is externally observable — a schema check, a downstream test — in which case it is not a vibe but a validated retry.