Is a Faster Model Actually Faster? Test the Whole Job — Morgan Suo, MiniMax

A faster model only helps if the finished job gets faster. The talk walks through inference optimizations and how each can hide accuracy or wait-time costs, then gives a method for judging a model switch.

• inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.

• videoAI Cut Our Research Time From 7 Days to 15 Minutes — Gareth Yoder, Vanguard
• videoA Bank Built Its Own Coding Agent. It Took Off — Felipe Felisola Caso & Francesco Galletta, Monzo
• videoSame GPU, 50% More Output: Why the Operator Matters — Oliver Kennon, SemiAnalysis
• videoWhy AI Agents Will Need Their Own Bank Accounts — Lincoln Murr, Coinbase

• articleMinimax M31fMiniMax editorial sitemap
• videoSame Model, Different Speed: Why Your Inference Provider Matters — FriendliAIAI Engineer
• videoThe Model Swap Workshop: GPT-5.5 vs Kimi vs DeepSeek vs MistralAI Engineer

Checking sign-in…

Loading comments…