Jev hype explained: a classifier that picks answers instead of writing them, fast and cheap

eptwts · x · 2026-09-19

X user eptwts summarized the recent hype around Jev, a small model that works very differently from mainstream LLMs.

Instead of generating an essay word by word like the LLMs we know, Jev takes a situation plus a list of possible answers and picks one with a confidence score. That means three things: it technically can't "hallucinate" since it can't make things up, it's extremely fast and cheap, and it's best suited for huge systems that require massive amounts of classification and decision-making based on inputs.

Original post →

More from Models

Models channel →