TypeSafe's Jev classification model goes viral, ushering in intent-based software
danshipper · x · 2026-09-27
Every breaks down Jev, the decision model released Sept 15 by stealth AI lab TypeSafe. Instead of generating text, Jev classifies it — cheaply and accurately handling judgment calls like spam triage, AI-slop detection, and support-ticket escalation at scale. Demos (games, search re-ranking, intent inference from speech and gestures) have gone viral, with one passing 1M views. The thesis: Jev is a decision model, not a chatbot, and it's kicking off intent-based software.
Related event: Jev, a judgment-only model, takes off on Vercel AI Gateway(8 posts)→
More from Models
- Theory: Typos Disrupt LLM Tokenization, Which May Explain Why AI Text Has a Distinct Smell — menhguin · 2026-11-11
- LMArena co-founder explains AI evaluation methodology and policy in new podcast — MattPerault · 2026-11-11
- Runway open-sources Praxis-1, turning video pretraining into real robot control — runwayml · 2026-11-11
- DeepMind launches AlphaGenome 2, spotting nearly 2x more gene-regulating mutations — GoogleDeepMind · 2026-11-11
- MazeBench: Fable 5.2 scores 15%, near-frontier at half price; Gemini 4 Carbon 11% — patience_cave · 2026-11-11
- ERNIE 5.5 Flash Preview enters LMArena Battle Mode for crowdsourced ranking — arena · 2026-11-11