Why Inference Matters 12x More Than Training | YC Paper Club
Source
youtube.com
Author
Y Combinator
Date
Why it matters
Explains why the same open model behaves differently across hosts and how caching and compilers cut inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition → cost. Useful for anyone choosing providers or building AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → infrastructure.
Terms in this piece · Glossary
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
