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.
andai 44 minutes ago [-]
>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...
simedw 23 minutes ago [-]
I haven’t run extensive tests yet, but larger models also get better at memory.
thorum 57 minutes ago [-]
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?
gr_norm 44 minutes ago [-]
Why would you do that instead of having the model do the task you're using the UI for? It could generate UI widgets on-the-fly as needed to take richer inputs.
skohan 22 minutes ago [-]
It might be fine for one-off applications, but it's incredibly inefficient for something that has to be done over and over.
Why would you use a GPU and gigabytes of VRAM running a non-deterministic process for something a program can do on the CPU in milliseconds with kilobytes of memory?
hnlmorg 7 minutes ago [-]
Probably for the same reasons most of our desktop applications have become slow Chromium instances consuming multiple GBs of RAM, each:
It’s cheaper to hire developers, and quicker to ship software. The user experience be damned.
antonvs 8 minutes ago [-]
I don't really disagree, but... why do we use Javascript for so many UIs? Badly designed web pages with ads can easily use gigabytes of RAM.
Edit: oh, I saw you wrote a related comment after I posted this. So you already know that direct LLMs for UIs are all but inevitable...
skohan 43 minutes ago [-]
We had decades to work on making software more performant, but instead most users' space-age 2nm chips spend most of their time running Javascript because it was faster to make software that way.
winrid 13 minutes ago [-]
even my ten year old laptop browses the web fine ^_^
If I had to complain about any site/app it'd be datadog... each tab uses like 1gb in firefox.
oilkillsbirds 2 hours ago [-]
Very cool. Fun project. I feel like there’s a wide field to be explored once you understand fine tuning good existing models
psandor 1 hours ago [-]
Reminds me of this project from Microsoft. A Quake II “simulation” model where the whole application was just a model.
Wait, how did it `sleep 3`? I thought LLMs didn't have a concept of time
peder 53 minutes ago [-]
It’s still rendering frames constantly, no? So it just figures the next X frames are all doing nothing?
simedw 19 minutes ago [-]
Normal only keypresses invoke the next ”frame”. There is a sleep token that the runner could use to indicate that time is moving.
sprobertson 53 minutes ago [-]
from the post:
Time is an input too. If nothing is pressed, the model gets a WAIT token with a duration instead of a key, which is how snake keeps moving on its own.
yjftsjthsd-h 46 minutes ago [-]
That seems as likely as anything, but that just moves the problem to counting, doesn't it? The model gets the duration, but I was under the impression LLMs struggled with the arithmetic that would make that useful.
skohan 38 minutes ago [-]
Idk about Qwen 2.5 Coder that this is based on, but modern models don't struggle with arithmetic. I see Qwen 3.8 do long-hand math in thinking traces (ie. it outputs 17+35+12=64 in the thinking trace) so I would imagine this is something they train into the model specifically. Sometimes it creates and runs a simple python script to check its work.
__mp 1 hours ago [-]
It would be interesting to expose this on the internet. I wonder what the scrapers etc… would do with it.
32 minutes ago [-]
obilgic 2 hours ago [-]
There was a whole fake gui OS with similar concept right
Where is the point of this project if i have terminal ?
antonvs 2 minutes ago [-]
This will allow you to delete your terminal app and, eventually, all other binaries in your system!
YmFzZTY0ZGFkZHk 1 hours ago [-]
Sometimes it's just fun to do something absurd because you can. This is one of the reasons software is exciting.
mehmetoguzderin 1 hours ago [-]
Terminal world models have many applications, but empirical observation of successful pretraining or fine-tuning can be significant for encapsulating from rather expensive Bash traces, such as ones obtained from systems with scarce accelerators, etc.
aghuang 37 minutes ago [-]
Was thinking the same thing. I just run my usual terminal and get to work.
good-idea 1 hours ago [-]
because curiosity is the most fun of virtues!
dotancohen 2 hours ago [-]
Because it was there
Rendered at 06:58:17 GMT+0000 (Coordinated Universal Time) with Vercel.
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...
Why would you use a GPU and gigabytes of VRAM running a non-deterministic process for something a program can do on the CPU in milliseconds with kilobytes of memory?
It’s cheaper to hire developers, and quicker to ship software. The user experience be damned.
Edit: oh, I saw you wrote a related comment after I posted this. So you already know that direct LLMs for UIs are all but inevitable...
If I had to complain about any site/app it'd be datadog... each tab uses like 1gb in firefox.
https://www.microsoft.com/en-us/research/articles/whamm-real...
Time is an input too. If nothing is pressed, the model gets a WAIT token with a duration instead of a key, which is how snake keeps moving on its own.
https://www.youtube.com/watch?v=z3pV6FHvcgM
The tmux thing had me confused for a moment until i realized it was emulating tmux. Super fun. Is the model window width aware?