Jev Selects Actions for Geneva Pilot
Jev is a new calibrated-decision model (RLCD) designed to choose an action from a finite set. In Le Guet, a pilot around Geneva, it receives a screen, possible actions, and a natural-language goal, then decides what to do next in one request.
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.
- Jev-Powered Rust Survival Game
Anthony Eckert says he has a Rust survival-game clone in pre-alpha, with an agent playing using Jev. He says crypto rewards are coming soon, with browser play and full agent support planned for tomorrow.
- A Jev-Made Unity Build
Kevin Kern says the build was made with Jev, GPT Live, Blender, Unity, and more.