WorldTUI: I trained a 360M model to pretend to be a terminal
A developer has fine-tuned a 360M-parameter language model to simulate a terminal environment without an underlying shell or filesystem. The model predicts screen changes based on user input, demonstrating the potential for world models in application design.
Why it matters
This experiment explores the frontier of generative AI, moving beyond text generation toward models that can maintain consistent, interactive virtual environments.
TL;DR: I fine-tuned a 360M-parameter language model to act as a terminal. There's no shell or filesystem behind it: every keypress goes in, and the model predicts how the screen changes. It can create files, run vim and tmux, play snake, and usually remembers what you wrote a few commands later. The biggest wins were teaching it to repair its own mistakes and decoding screen rows in parallel. Try it in your browser (208 MB) and type pythoon to see that it's not a real shell.
The demo is designed for a desktop browser with WebGPU and a physical keyboard. Chrome or Edge is the best place to try it. It should work on a modern phone, but painfully slowly.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in