alt Hacker NewsWorldTUI: I trained a 360M model to pretend to be a terminal
Comments
>I used Qwen2.5-Coder-0.5B as the starting point. I needed a small model to get close to realtime performance. Being a coding model, it had also already seen plenty of CLI usage.
Interesting. I wanted to ask, how that model compares with the fine-tuned version, but I just saw the author provided benchmarks. Interesting that fine-tuning improved the memory so significantly, wouldn't have expected that.
Though, on second thought, I had an experience where I was able to, as a human, fine-tune my memory beyond what I previously thought was possible!
Reminds me of one of my favorite jokes.
Excuse me, can you tell me how to get to Carnegie Hall?
—Practice, man... Practice...
Very cool to do this as a Terminal!
I did it for web apps last year, basically a web server that feeds all requests into an LLM.
I wonder how much a small model could do if it had a tool calling API for a filesystem, an embedded busybox, and a single output token for 'emit what busybox would do here'. Then presumably the model parameters could learn everything that diverges from what busybox can handle.
Very cool. Fun project. I feel like there’s a wide field to be explored once you understand fine tuning good existing models
It would be interesting to expose this on the internet. I wonder what the scrapers etc… would do with it.
Reminds me of this project from Microsoft. A Quake II “simulation” model where the whole application was just a model.
https://www.microsoft.com/en-us/research/articles/whamm-real...
I tried it and is not working remotely as close as the demo gif. It keeps telling me that "test1" folder that I want to create already exists (not true), then letting me do "mkdier test2" (sic) but then the folder is not there when ls. I mean all its expected, this has no state, follow no rules and is making up things from the current context, but is not as "magical" as I thought when watching the demo.
Wait, how did it `sleep 3`? I thought LLMs didn't have a concept of time
BUG: Running in Firefox makes every keypress a slow motion show. It decodes every keypress instead of sending a command with Enter key
Wow! This this reminds me of when we tried doing this with gpt 3 and.. it worked!
The tmux thing had me confused for a moment until i realized it was emulating tmux. Super fun. Is the model window width aware?
[flagged]
[dead]
[flagged]
I regretfully suspect this actually is the future of UI. You just need smart local models running fast enough to keep the framerate high, but that’s inevitable in the long term, isn’t it?
Very very cool! Impressed that it can be done with only fine tuning
On a very similar theme, I recently built a “lossy git”, which stores your code by training a neural network, then it generates the code back to you on checkout
* web demo: https://nicobrenner.github.io/lossy-git/demo.html
* cli version: https://nicobrenner.github.io/lossy-git/
The web demo runs entirely on the browser, both the version control and the neural network training/inference. You can commit and checkout both images or code - you can also paste/“upload” your own images, no server requests (everything clears from the page on reload)