Concurrent Fruit-Fly Foraging Simulation
N DIVIJ built flysim, a foraging world where a fruit fly finds sugar and dodges a predator. It runs two decision layers concurrently in the same world.
N DIVIJ@godlovesu_n𝕏
flysim is a foraging world where a fruit-fly has to find sugar and dodge a predator, and you swap out who makes the decisions. I put two decision layers in it and ran them at the same time. Same world, same body, same predator — concurrent, not lockstep. Jev by @typesafeai lived 30 ticks in 13.2 seconds for $0.000834. gpt-6-astra took 101.9 seconds and $0.121280. 145x the cost. 7.7x per decision.
The comparison used the same body and predator, but was not lockstep. Jev lived 30 ticks while gpt-6-astra took 101.9 seconds; the author reported gpt-6-astra cost 145x more and 7.7x per decision.
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.