Playground
CommunityJev Demos & Experiments
OSS Jev Decision Gradio
A Gradio-based Hugging Face Space by gyanbhambhani titled OSS Jev — Choice / Score / Noul, presenting the three Jev decision shapes in a browser interface that sleeps when idle.
- Format
- Playground
- Reading time
- 1 min
- Published by
- Community
- Added
- Oct 2026
Questions about this entry
Short answers drawn from the linked project or page.
It is a Gradio app titled OSS Jev — Choice / Score / Noul, presenting those three Jev decision shapes in a browser interface rather than as a text chat.
The page states the Space is sleeping due to inactivity. Use the Restart this Space control on the page to bring it back up before trying the interface.
No. It is published under the Hugging Face account gyanbhambhani, which makes it a community Space rather than an official TypeSafe AI property.
The Space name and page indicate a Gradio app, so the interface is a Gradio web UI hosted on Hugging Face infrastructure.
The Space page includes Files and Community tabs, which is where the app files and discussion live. The page itself does not describe licensing terms.
The page does not document credentials or sign-in requirements. Access is through the hosted Space interface, subject to the Space being awake.
If you need documented configuration, stable uptime, or reproducible numbers, a sleeping community Space is a poor fit; use the official SDKs or cookbooks instead.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Standard One SH (StandardThinking)
LinkedIn: What multimodal decision models actually change, and what they do not.
LinkedInJevDirectory.org
Hacker News: Decision Index 0.2.1 scores open reproductions of Jev on a frozen suite.
jackbravo4 pointsDecision Index 0.2.1 – 70 open reproductions of TypeSafe Jev's Decision ModelRead the thread on Hacker NewsHacker News: Pointer to a DiffusionGemma plus vLLM tutorial for a Jev-shaped classifier.
1 pointHow to build a Jev-style classifier with DiffusionGemma and vLLMRead the thread on Hacker NewsMore Jev resources like this
Browser and terminal demo that ranks emoji against a free-text query by sending one Jev score question per emoji, then filtering by a tunable score floor and limit. Includes a bench harness over saved queries.
Jev Demos & Experiments#madewithjev#demo#typescript
Communitynischal94/emoji-sift
A Beam-hosted playground for comparing open-source alternatives to Jev and running any of them as an API. You edit a state and typed questions in the browser, then call the same model through an OpenAI-compatible endpoint with a workspace token.
Jev Demos & ExperimentsPlayground#community#catalog-import#madewithjev
Community
An interactive ZeroGPU demo of AutoTrust's JEV-9B: System 1 answers noul, choice, and score questions in one prefill pass with calibrated probabilities, while an Escalate tab hands low-confidence cases to the untouched Qwen3.5-9B base.
Jev Demos & ExperimentsPlayground#community#playground#demo
Community
AutoTrust's live game-arena demo: watch JEV-27B play Mario, a 3D Rubik's Cube, and Tetris while a side panel reports action probabilities and per-decision inference time, alongside a decision lab and a ViZDoom arena.
Jev Demos & ExperimentsPlayground#community#playground#demo
Community
A three-lane demo of pngwn's System One 4B scorer: one prefill plus a batched forward for every option branch, a naive per-option equivalence check, and a Qwen3.5-4B instruct baseline generating JSON.
Jev Demos & ExperimentsPlayground#community#playground#demo
Community
A static page that races three LLM judging gates — Laya, JEV, and zero-token ZTC — on the same Tetris board with identical pieces, proposals, and noise, publishing paired-match results and the measured constants behind them.
Jev Demos & ExperimentsPlayground#community#playground#demo
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.