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: Self-described ChatGPT co-inventor launches decision model Jev(36 posts)→
More from Models
- OpenAI's new quirk: chat mode now has a usage cap while work mode doesn't — koltregaskes · 2026-09-16
- MindTopo benchmark: best MLLM scores 54.1% vs 97.4% human on topological reasoning; GPT-6 Astra needs 8+ hours per task — yining_hong · 2026-09-16
- all-MiniLM-L6-v2 still trending on Hugging Face, its creator says stop using it — tomaarsen · 2026-09-16
- HF researcher publicly questions Claude limits: monthly exhausted but weekly 84% left — NielsRogge · 2026-09-16
- Meta's promised Muse Spark open weights are over a month late and counting — RishiFurfox · 2026-09-16
- Ex-Huawei researcher: AI is great at small-step optimization, but taste and system design remain out of reach — yangyi · 2026-09-16