devwithjevRuns Snake Decisions Locally
Laya beat Jev 43 to 1 in Snake with Wi-Fi turned off, making 86.4 decisions per second against Jev’s 3.2. Laya is an open-weights decision model with 421 million parameters running locally from a 1GB footprint.
View on X time8.9ms against a 258.3ms round t
chewa@0xchewa𝕏
Laya beat Jev 43 to 1 with the wifi turned off 86.4 decisions per second against 3.2. 1,281 moves against 47 left side is Laya, an open weights decision model, 421 million parameters, running locally off a 1GB footprint. right side is Jev 1.13.0 over an API. both got the identical typed decision schema and the identical snake, same seed, same 30 seconds predict time 8.9ms against a 258.3ms round t
Both models used the identical typed decision schema and snake, with the same seed and 30 seconds of predict time. Jev 1.13.0 ran over an API; Laya made 1,281 moves against Jev’s 47.
Also filed under Games & real time
- 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.
- StarCraft Agent for Fast Tactical Decisions
Jev_Star is a StarCraft agent experiment that uses Jev for fast tactical decisions.
- AI-Town Character Action Simulation
JevTown is an AI-town simulation where Jev selects character actions and responses.
- Jev-Powered Drone Swarm Simulation
The project simulates a drone swarm using Jev for reflex decisions and collision avoidance.