InTowards AIbyCarmine De Stefano·Sep 22Build a browser extension with JevHow I built Grounds, a Chrome extension that instantly flags whether a page argues its claims or merely asserts them
InGenerative AIbyJim Clyde Monge·Sep 19New Jev Model is Insane! 200x Faster & 400x Cheaper Than Frontier ModelsWhy TypeSafe AI just flipped software automation on its head, and why your app probably does not need another expensive chat model.A response icon22
InGenerative AIbyJim Clyde Monge·Sep 19New Jev Model is Insane! 200x Faster & 400x Cheaper Than Frontier ModelsWhy TypeSafe AI just flipped software automation on its head, and why your app probably does not need another expensive chat model.A response icon22
Agent Native·Sep 19Top 10 JEV Use Cases in Agentic Apps. Ranked by Theoretical Gain Over LLMs.Fast model reacts, slow model plans: where a typed decision layer beats a full LLM call on speed, cost, and reliability.A response icon10
Agent Native·Sep 18$0.0001 Decision Model That Will Replace Millions of LLM CallsThe most expensive part of many agent systems is the thousands of tiny decisions wrapped around it.A response icon2
DhanushKumar·6d agoJev AI: The Rise of System One Models and a New Interface Between AI and SoftwareThe current generation of artificial intelligence has been built around a remarkably powerful abstraction: give a model some information…A response icon2
InAutom8lybyMark·2d agoJev is the best decision model. Here’s what to run when you can’t use it.We put seven open-source Jev look-alikes on a single 8 GB GPU for teams whose data isn’t allowed to leave the building. One of them is good…
Vidit Shrimali·14h agoJev without JargonsWe have been using LLMs like a hammer for every AI problem, even simple decisions. Jev handles those decisions in milliseconds at a…
Hitesh Sahni·14h agoJEV Explained: The AI Model Built to Make Decisions, Not Have ConversationsWe are used to thinking about AI models as systems that talk to us.
Eugenii Shevchenko·17h agoThe Model That Never Writes Code: Building a Clojure Synthesizer from Multiple-Choice AnswersHow I stopped asking a language model to write programs, and started asking it to choose.
Alvar Laigna·17h agoSystem One Next to the LLM: First Week in a Procurement AssistantWhat happens when you put a fast, calibrated System One model next to an LLM planner in a public procurement assistant: latency, costs, and…
Neeraj Garg·22h agoJev vs. Laya: The Rise of Super-Fast ‘System 1’ AI Models That Ditch Autoregressive TokensIf you are currently routing customer support tickets, classifying JSON payloads, or evaluating safety guardrails by passing prompt text to…