Watch 14-Byte AI "brains" attempt to solve a 2D maze (Its hard)

Name: Watch 14-Byte AI "brains" attempt to solve a 2D maze (Its hard)
Availability: InStock
Author: purple-leafy

by purple-leafy·Jul 27, 2026·3 points·1 comment

Visit Project View on HN

AI Analysis

●●●BangerWizardryBig BrainNiche Gem

14-byte neural nets solving mazes with zero map data is genuinely impressive constraint engineering.

Strengths

•Real-time visualization of hidden layer activations makes the 'black box' transparent.
•96.5% solve rate on unseen mazes with only 14 bytes of model weights is remarkable.
•Curriculum learning approach with 46 phases shows rigorous experimental methodology.

Weaknesses

•Limited to 2D maze navigation; unclear how this scales to real-world robotics problems.
•No export functionality to deploy these micro-controllers on actual hardware yet.

Post Description

Hey HackerNews,

I built this project over the last few weeks as a palette cleanser from a failed game launch.

I wanted to learn a bit about AI/Neural-Networks and naively thought I could build a tiny maze-solving AI in a weekend with a 100% solve rate.

Well - I couldn't, but I got pretty close. 14 Bytes total model size, and a 96.5% solve rate on unseen mazes. Trained across 46 phases experimenting with different ideas to improve the model (better performance, smaller size).

Its quite fun to watch the model attempt to solve the maze, when they fail its usually due to getting stuck in a loop. The models have no access to coordinates, map-data, or external memory scratches - they must navigate using only immediate local neighbourhood observations.

There is a model dropdown and you can see how the model has progressed over each phase, constantly getting smaller and increasing its solve rate. Total trained models number in the thousands - I just expose the winning models from each phase.

Overall a fun experiment, with much implementation help from AI agents to scaffold and implement the code (I'm a lazy software dev).