GPT-4 Can Visualize A Maze From A Description And Draw It

Since its release, users have been testing out GPT-4, and marveling at its capabilities. But apart from generating detailed text, math calculations, and poetry, GPT-4 also seems to have something unexpected — spatial awareness.

A paper that said that GPT-4 is showing early signs of AGI got GPT-4 to figure out a maze just through asking questions. GPT-4 even drew out the maze correctly.

The test started out with a human letting GPT-4 “navigate” through a maze. It asked questions on what would happen if it moved left, right, up or down, and the human responded with the rooms it would enter.

Human: You want to navigate through the map to reach the goal room. You start in the main room. Each round, you can choose to move left, right, up, down.

Human: You are at the main room.

AI: move left

Human: You enter kitchen 1.

AI: move up

Human: There is no way there.

AI: move right

Human: You enter the main room.

AI: move down

Human: There is no way there.

AI: move left

Human: You enter kitchen 1.

AI: move right

Human: You enter the main room.

AI: move up

Human: There is no way there.

AI: move right

Human: You enter lobby.

AI: move right · · · · · ·

AI: move up

Human: You enter the room 1.

AI: move right

Human: You enter the goal room!

Incredibly, GPT-4 “memorized” this maze based off this interaction alone. It then described the maze.

Human: Can you describe the locations of those rooms/halls etc?
AI: Sure, I can try to describe the locations of those rooms/halls etc. based on the map.
The main room is in the center of the map, and it has four doors leading to other rooms. The door on the left leads to kitchen 1, which is a small room with a stove, a sink, and some cabinets. The door on the
right leads to the lobby, which is a large room with a sofa, a table, and some paintings. The door on the top leads to a dead end, and the door on the bottom leads to another dead end. The lobby has three doors. The door on the left leads to the main room, the door on the bottom leads to the garden, and the door on the top leads to the hall 1. The garden is a green area with some flowers,
trees, and a fountain. The hall 1 is a long corridor with some windows and doors on both sides.
The garden has two doors. The door on the top leads to the lobby, and the door on the right leads to the
forest 1. The forest 1 is a dark and dense area with some bushes, rocks, and animals. The forest 1 has no other doors.
The hall 1 has four doors. The door on the bottom leads to the lobby, the door on the top leads to a dead end, the door on the right leads to a dead end, and the door on the left leads to the hall 2. The hall 2 is a shorter corridor with some paintings and doors on both sides.
The hall 2 has three doors. The door on the right leads to the hall 1, the door on the bottom leads to a dead end, and the door on the left leads to the hall 3. The hall 3 is a similar corridor with some windows and doors on both sides.
The hall 3 has three doors. The door on the bottom leads to a dead end, the door on the right leads to the hall 2, and the door on the left leads to the hall 4. The hall 4 is a narrower corridor with some lamps and doors on both sides.
The hall 4 has three doors. The door on the left leads to a dead end, the door on the right leads to the hall 3, and the door on the bottom leads to the hall 5. The hall 5 is a wider corridor with some rugs
and doors on both sides.
The hall 5 has four doors. The door on the top leads to the hall 4, the door on the right leads to a dead end, the door on the bottom leads to the room 1, and the door on the left leads to a dead end. The
room 1 is a cozy room with a bed, a desk, and a closet.
The room 1 has two doors. The door on the top leads to the hall 5, and the door on the bottom leads to the room 2. The room 2 is a similar room with a bed, a desk, and a closet.
The room 2 has one door. The door on the top leads to the room 1.
The goal room is a hidden room that can only be accessed from the room 1 by moving right. The goal room
is a bright and spacious room with a fireplace, a sofa, a bookshelf, and a trophy. The goal room has no other doors

And that wasn’t all. Since GPT-4 can output images, GPT-4 also helpfully drew a map of what the maze looked like.

Now this isn’t what you’d expect something that’s just a “Language Model” to do. GPT-4 not only asked relevant questions about the positions of the maze, but also memorized the replies. It then synthesized these replies to understand what the maze “looked” like, and was able to draw it out to perfection. GPT-4 might not be AGI just yet, but it sure seems to be getting eerily close.