Jev launches: a decision-optimized model claiming 20-200x speed and 40-400x cost gains
FrankFelixAI · x · 2026-09-16
CompleteSkeptic, who says he co-invented ChatGPT, released Jev, a frontier model optimized for composable decision-making, claiming 20-200x speedups and 40-400x cost reductions (free output tokens), trained via a new method called RLCD.
NathanFlurry's hype-free explainer: Jev doesn't replace GPT or Claude — it's a "really smart switch statement," like 2016 ML classifiers with 2026 intelligence. It classifies, routes, scores, and ranks among predefined options (255 max per shot), outputs confidence, and can pick branches, tools, models, or sub-agents, judge/verify LLM outputs, and label rows at scale. It cannot write code, generate language, or reason step by step. Expected pattern: LLM proposes options → Jev decides → code executes.
Related event: TypeSafe exits stealth with decision model Jev and RLCD training method(86 posts)→
More from Models
- 'You Can Feel the Gradient Slopes': Dev Contrasts Benchmaxxed RL Models vs General Ones — theteknosaur · 2026-11-02
- LightOnOCR-3 Launches: Tops FRBench, Adds Layout Structure and Chart Extraction — IgorCarron · 2026-11-02
- NVIDIA's Kumo Is a Family of Four Tabular Foundation Models, Not Just One — pandeyparul · 2026-11-02
- SemiAnalysis: safety classifiers are underrated — Meta's Muse tops cyber benchmark at 35.2% — ThomasScialom · 2026-11-02
- DeepSeek V4.1 Flash 1017 wins over a longtime closed-source-only user: fast, cheap, reliable — _bachrc · 2026-11-02
- Local quants vs Claude on 9 real private bugs: 3-bit costs thinking time, not score — FeydRowan · 2026-11-02