Skip to content

JEV-27B Live Demo

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.

Format
Playground
Published by
Community
Author
AutoTrust AI
Last verified
Oct 2026

Highlights

  • Three live games: Mario on original NES World 1-1, a 25-turn 3D Rubik's Cube scramble, and Tetris with gravity accelerating to maximum speed until 20 lines.
  • The panel shows the selected action, option probabilities, and current and average per-decision inference time; Mario movement and jump are separate calls.
  • The interface and ViZDoom simulator run on CPU; the model worker runs on AutoTrust's B300 deployment, and all run traces and rendered frames stay there.
  • The Doom arena supports manual play, one requested JEV move, or ten consecutive model decisions; game sessions expire after ten minutes of inactivity.
  • The decision lab covers multiple choice, true/false, and 0-5 scoring on text or images; the demo reel holds ten recordings and six benchmark charts.

Watch out

The Space runs on CPU Basic and needs a compatible JEV backend: set JEV_BASE_URL and keep JEV_API_KEY in Space Secrets. Image questions go through Qwen2-VL-2B-Instruct because the deployed JEV checkpoint is text-only, which the card calls a vision-assisted pipeline. The Space contains no Mario ROM, and the recorded reel dates to a September 27, 2026 benchmark comparison.

Questions about this entry

Short answers drawn from the linked project or page.

Related terms

Glossary definitions related to this entry.

More Jev resources like this

A browser dino run steered by small decision models: each obstacle becomes a one-line text question answered through open-jev, with a three-course index comparing models in real-time or turn-based mode.
Jev Demos & ExperimentsPlayground#community#playground#demo
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
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
A Gradio playground for Jev-Omni: give a situation plus a question with options and get one probability per option from a single forward pass, with no generated text, from a Gemma 4 12B IT fine-tune.
Jev Demos & ExperimentsPlayground#community#playground#demo
Community
A Gradio playground for KaLM-Jev Small structured judgments: choice, score, noul, and mixed JSON questions return probability tables and full responses without generating answer text on shared ZeroGPU.
Jev Demos & ExperimentsPlayground#community#playground#demo
Community

From the Jev guides

Original write-ups on what this entry is for.

A game tick is a state plus a legal action list. How Clash Royale, Minecraft, and the earlier Mario, Pokémon, StarCraft, and drone loops ask Jev one step at a time.
Jev Demos & Experiments#gaming#agents#control
Read article
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai