Jev, a classification-not-generation model, goes viral with 1M-view intent demos

danshipper · x · 2026-09-25

Frontier lab TypeSafe released Jev on Sept 15: a model that classifies text and structured data instead of generating it. Fast, cheap and accurate enough to handle judgment calls you'd never pay an LLM to make at scale — is this email urgent, does this paragraph sound AI-written, should this support ticket be escalated. Demos of Jev playing games, re-ranking search and filtering social feeds are flooding X; one demo inferring user intent from speech and gestures passed 1M views. The piece frames this as the dawn of intent-based software and explains how to turn subjective questions into Jev checks.

Original post →

More from Models

Models channel →