Parallel-Path Doom Player

A Doom-playing system uses Jev to pick moves, tries several futures in parallel from the same checkpoint, and continues from the best outcome.

View on X

toks@toksdotdev𝕏

i got jev + an llm playing doom, with a twist: try several futures, then keep playing from the best outcome. jev picks the moves. a custom harness uses @microsandbox to run attempts in parallel from the same checkpoint. the llm reviews what happened and guides what to try next. not enough? it rewinds to an earlier checkpoint and tries another path.

Sep 18, 2026X postsView on X

A custom harness uses @microsandbox to run attempts in parallel. An LLM reviews what happened and guides what to try next; the system can rewind to an earlier checkpoint and try another path.

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.