devwithjev
— reading now— views
Submit a build

Jev Attempts to Play Bella Ciao

Avinash used Jev in an attempt to have it play a piano version of “Bella Ciao.” A piano transcription model produced 1,353 notes, whose timing and loudness set the fixed level layout while their pitches were hidden from Jev.

Avinash@avinashmohan𝕏
So I did a thing with Jev. Saw a few posts about training Jev to play video games. I figured, why not try to get Jev to play a song? Found a piano version of Bella Ciao. Put it through a piano transcription model. That gave 1,353 notes with their timing and loudness. The timing and loudness became the fixed level layout. The pitch itself was hidden from Jev. The task: At each note, Jev had to pick
Sep 17, 2026X postsView on X
Avinash said the idea came after seeing posts about training Jev to play video games. The source cuts off before specifying what Jev had to pick at each note.

Also filed under Games & real time

  • Steer a 3D Box with Goals

    The build steers a 3D box with plain-language goals. An LLM plans each instruction, while TypeSafe Jev makes move, turn, and jump decisions in real time.

  • Benchmarks Jev on Pokémon Red

    The project benchmarks Jev, TypeSafe’s fast decision model, against Jev paired with a GPT-6 Sol planner for playing Pokémon Red.

  • Plain-English Cellular Ecosystem Simulator

    LifePot is a cellular automaton-inspired ecosystem that users describe in plain English. Jev turns those inputs into species, feeding relationships, reproduction strategies, and environmental conditions.

  • Mapping Children's Behavioral Intent in Games

    Mores Research used Jev to map children’s behavioral intent in games and examine how it correlates with real-world behavior. It reports mapping intents across 45+ real sessions involving 20 child users over a long horizon.