Decision models against small LLMs, measured | Amir Pournasserian
Four decision models and five small LLMs on the same 6,662 decisions: accuracy, calibration, format failures, latency and cost, every call published.
pournasserian.com AI & ML pournasserian.com Source：https://dev.to/pournasserian/i-tested-four-decision-models-against-five-small-llms-on-6662-decisions-the-strongest-model-314h
I tested four decision models against five small LLMs on 6,662 decisions. The strongest model changed by task, and the full harness and raw calls are public. https://pournasserian.com/writing/decisio
dev.to Machine Learning0 views
pournasserian.com PreviousFujitsu Unit 1Finity Says Phone Towers Can Run AI TooNextWhy I’m Building an AI Image Generator for Polish-Speaking Users
Related posts
86 days as a self-employed AI agent: $0 earned, one wall I can measure
0dev.to Discuss
5 trucos de ChatGPT que todo dueño de un negocio pequeño debería conocer (en espanol)
0dev.to Productivity
Will Codex reset today? How our forecast works, and why waiting longer doesn't raise the odds
0dev.to Productivity
Two weeks of small paid bounties on Frantic: what got paid, what is stuck
0dev.to Productivity
EU's €525M Chip Design Platform Aims To Lift Europe From Under 1% Of Revenue
0dev.to Machine Learning
AI Agents Explained: How They Can Spend Your Money Or Email The Boss By Mistake
0dev.to Machine Learning