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.
Related event: Classification Model Jev Goes Viral for Fast, Cheap AI Judgments(2 posts)→
More from Models
- Gemini re-renders images as text when vision is removed, dropping only 6% WSR — zacharynado · 2026-11-12
- Google's Physical-Engineering's Last Exam: all 14 frontier models score below 50% — dl_weekly · 2026-11-12
- Commit leak reveals unreleased Gemini 4 variants: Argon, Hydrogen and Helix (unconfirmed) — BlackHC · 2026-11-11
- Rewiring just 89 of 442,368 neurons in Qwen3-8B matches full SFT for a persona — maxsloef · 2026-11-11
- Unsloth ships Qwen3.8-27B Dynamic V3.1 GGUFs with 5-10% accuracy gains — danielhanchen · 2026-11-11
- Zvi: being forced back to an older model is the best reminder of AI progress — TheZvi · 2026-11-11