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.
More from Models
- OpenAI weighs 'Pro Max' ChatGPT plan that would charge extra for longer tasks — ryanmerket · 2026-09-25
- GPT 6.1 'Astra' Rumors Swirl as OpenAI's Release Pace Stuns Observers — bindureddy · 2026-09-25
- GPT-6 models duel in DOOM: Astra wins 82.5% of 120 agent matches — OpenAIDevs · 2026-09-25
- User warns Sol-6 high mode hallucinates finished work, forcing constant rework — Babayaga1664 · 2026-09-25
- Alexandr Wang amplifies Muse skepticism post calling the model 'underwhelming and useless' — maheen_sohail · 2026-09-25
- The AI Meme: Wait Until Your Project Is 78% Done, Then They Nerf the Model — BLUECOW009 · 2026-09-25