Stop Paying for Frontier Models

Most of us reach for a frontier model by default and pay for it on every call — in latency, energy, cash, and in everything that leaves the stack. For most of those calls, a small local model would do the job. RL Nabors — former Meta/React core team and AWS alum — covers the vocabulary you need to reason about model performance (capability evals, golden datasets, LLM-as-judge) and walks through real cases: a local agentic harness replacing a frontier call, an in-browser moderation classifier defended with production-trace evals, and a generative summarization feature where the rubric turns out to be harder than the model. You'll leave with a framework for deciding when to choose large-and-off-prem vs small-and-local, and how to measure your way to the answer instead of guessing.