What people are shipping with Jev.

Jupyter Notebook | 17 stars | Typesafe.ai System One Model Jev navigating a Neo4j graph by using a classifier over neighbouring relationships

16 hours ago ... Jev by TypeSafe returns typed decisions with confidence, not text, at up to 200x LLM speed. Why a non-hallucinating decision model fits AI agents.

1 day ago ... be testing Jev, TypeSafe's System One model designed for fast, inexpensive, and structured AI decisions ... demo shows how it can support fast browser ...

9 hours ago ... It seems that the automated bot player is using Jev to determine where to shoot and when to shoot, based on calculating probabilities and then acting on those 

16 hours ago ... Typesafe pitches Jev as a “system one model,” a different architecture built ... A Minecraft bot built by a developer using Jev reportedly ran for two ...

9 hours ago ... TypeSafe AI calls Jev its first System One Model, borrowing the “fast ... Start using Jev with AIHubMix. AIHubMix has added support for Jev, giving ...

10 hours ago ... OK, so this was made using JEV model from Typesafe API. It's a new model that they released. It's not like our traditional MLM, so it doesn't know how to ...

@sydneyrunkle Tool selection, determining if the main loop needs to run again - can also be helpful use cases of @typesafeai Jev.

@ownerofmarket @AsideAI @typesafeai So what’s better to use jev or a llm per cli when it comes to browser navigation and execution? @grok

@CryptoPraetoria @ownerofmarket @AsideAI @typesafeai Jev is better for browser navigation and execution. It chooses only from real page elements with typed decisions in ~70-500ms,

Had some fun taking Jev from @typesafeai for a spin, switching seamlessly between manual and AI-driven gameplay.

So here’s what I built.

@rauchg @typesafeai @vercel Default-auto with a safety reviewer on every command is the agent posture I want more CLIs to copy. @rauchg on @typesafeai fx (auto mode, reviewer on G

Three AI agents, one shopping page, all started at the same moment. Task: save my basket. gpt-4o-mini on its own: shared my email with the store's partners, then placed an order n

@MicahDail @netestapper @typesafeai A bunch of agents are also slapping together an experiment of a kind of Jev loop where, during a /goal, the agents consult to be able to evaluat

Same week TypeSafe launched Jev (@typesafeai / @CompleteSkeptic). Not a chatbot. Send state + typed questions. Get decisions with probabilities. The pitch is that it's very fast a

What happens when you let @typesafeai’s Jev choose where a burning cargo ship should go, or where a plane in trouble should land? I built an app to find out. The ships and aircraf

What happens when you let @typesafeai’s Jev choose where a burning cargo ship should go, or where a plane in trouble should land? I built an app to find out. The ships and aircraf

@i_am_za_man @typesafeai's Jev probably a good use case somewhere in here for when to trigger human in the loop. Still, generally speaking, a human actively monitoring agent reason

@K_aditya25 @typesafeai the latency win is less "Jev does browser" and more "stop paying an LLM to plan in prose". kyle's loop is the pattern: observe a11y as state, Choice over ca