Writing · draft
Model-offloading & the price of lost confidence
When a smaller or local model wins — and when the harness to trust it costs more than the model you saved.
Draft in progress. The full piece is being written here. The seed below is the through-line; I'll expand it into the finished essay.
Sending non-interactive work to a cheaper model can be a real win — until the verification and guardrails you need to trust its output cost more than the model you saved. The tradeoff is reliability, not just price; the harness is what makes the call legible.