patience, jimmy, openai is nothing without its good research takes time in the patience cave.
Jul 28 • 6 tweets • 3 min read
Introducing MazeBench, a 3D open world environment that evaluates long term planning with visual spatial reasoning.
It spans hundreds of rooms and puzzles. Today’s best agents cannot progress beyond the initial levels.
Agents need to go through 200+ rooms to find 100 hidden gems by completing Sokoban-like box pushing puzzles. The rules are simple, but difficulty increases at a rapid pace.
All puzzles were designed by hand and solved internally.
