Jev, the yes/no-only model, sparks debate: agents need judgment parts, not bigger engines
冷技术热思考 · wechat · 2026-09-23
Jev, a model that can only answer multiple-choice, scoring and yes/no questions with calibrated probabilities — no chatting, coding or vision — has stirred debate in the AI community. Its fixed answer space makes it fast and cheap.
Author Wang Yuan (ex-NetEase VP, founder of remio) frames it with a car metaphor: the LLM is the engine, context engineering is refining, and Jev is a sensor/ECU-class "judgment part." Emerging use cases include BrowserUse (picking which numbered element to click, cutting a Google Flights search from 9+ to 7 seconds), coding agents (filtering irrelevant tool output, routing easy tasks to cheap models, pre-screening risky code changes), and massive per-item classification (paper topics, spam, fraud, training-data curation).
Community tests show 7B models can be more accurate; Jev's value is turning judgment from "writing essays" into "filling answer sheets." The author plans to wire Jev into remio's retrieval filtering, memory arbitration and automation, under one principle: wherever a judgment suffices, don't generate.
Related event: Decision-Only AI Model Jev Goes Viral(2 posts)→
More from coding & agent
- Robotiq Takes Over Community ROS 2 Gripper Drivers With Three Official Open-Source Releases — lukas_m_ziegler · 2026-09-23
- Jay Alammar's 'Illustrated Guide to AI Agents' ships print copies October 6 — JayAlammar · 2026-09-23
- Shopify CEO's "slop grenades": 52.7% of workers admit sending unread AI output — max_gladysh · 2026-09-23
- Rails agent evals: OpenAI stays ahead, Luna Max the dark horse at 18% completion for just $11 — npew · 2026-09-23
- Agent regression testing benchmark: embeddings caught only 7/19 real answer changes — redhatpanda07 · 2026-09-23
- Three years of formal validation: AI now writes the Rust and proves it in Lean — carlk22 · 2026-09-23