Skip to content
JevDirectory.org
CommunityCookbooks & Demos294 starsVerified 2026-09-20

TypeSafe Mario

An experimental controller that has Jev choose NES inputs to play Super Mario Bros. from structured emulator telemetry instead of screenshots, logging every decision with probabilities and latency.

Category
Cookbooks & Demos
Published by
Community
Author
fhshaik
Added
2026-09-20
Tagscommunitypythongamesemulation

Highlights

  • Jev sees object-centric JSON: player motion, trajectory, up to three enemies, terrain, and reaction timing.
  • Each decision mixes a Choice for the next action, a Noul for jump usefulness, and a Score for danger.
  • Decisions are logged to artifacts/run-<timestamp>.jsonl with probabilities, latency, and outcome.
  • The dashboard shows the probability distribution, confidence, Jev latency, danger score, and reward.

Watch out

No ROM is included, so you supply a legally obtained copy, plus Python 3.13 or newer and a TypeSafe API key.

More like this

A camera-only MuJoCo quadrotor that uses Jev for tactical maneuvers at 2.5 Hz while classical perception and a 50 Hz reflex layer keep safety outside Jev, clearing a five-station course.
Cookbooks & Demos#community#python#robotics
Communityjev-drone
A video demo of a bot that asks Jev to decide buy or sell from a live price feed, then places real orders on Kuru's on-chain order book on Monad every 300ms block.
Cookbooks & Demos#community#x#video
Community
vogel ran Jev over 1,500 of his own emails to test classification quality and posted the results as a video, calling it the most impressive model he has tried for the task.
Cookbooks & Demos#community#x#video
Community
Back to all resources

From the community

Posts from builders shipping with Jev right now.

LLM-as-a-judge, sped up

Jev has spoken. It picked which model is AGI. 20–200x faster. 40–400x cheaper. This could make things like LLM-as-a-judge insanely fast and nearly free. (I tried a bunch of prompts and still didn’t burn through $0.10.)

Image
Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Reply

Instant compaction with Jev