News for hackers. Stuff that matters.

Show HN: Doom inside a 39M-parameter neural network

https://huggingface.co/spaces/kulikov0/micro-doom-world

Code: https://github.com/kulikov0/micro-doom-world Weights: https://huggingface.co/kulikov0/micro-doom-world

A 39M-parameter diffusion transformer predicts the next 128x96 frame from the previous 31 frames and the keys you press. It runs in the browser on WebGPU (it was tested on chrome and safari, I'm not sure how it runs in other browsers). Trained it on 1.5M frames of a scripted bot playing freedoom E1M1-E1M3

( no comments | on HN )

There are no comments yet.