<- Back
Comments (92)
- aurareturnHoly cow that’s amazing. I’d bet future apps will be built this way.
- nicoVery very cool! Impressed that it can be done with only fine tuningOn 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)
- saagarjha> Is it useful? Not really.So interestingly enough Anthropic has been using models of this kind for their alignment evaluations: https://alignment.anthropic.com/2026/reward-seeker/#:~:text=...
- andai>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...
- ernestrcThis is super cool! If you publish the weights I would love to bake it into Rune to run a screensaver hallucinating a terminal.
- ponyousOne of the first very cool demos I've seen of ChatGPT was in a post where the author prompted AI "pretend to be a terminal". Then went on to execute commands like `cd .fbi`, `ls files`, `cat files/confidential.txt`. Very fun demo. Looking forward to exploring similar idea with this terminal
- suhdonghwiIt's very tricky to make it hallucinate fake commands. I've been trying `dogsay` (instead of `cowsay`) but no luck. Any tips?
- h1fraI guess, with enough latency and/or memory, everything can be a filesystem
- amelius> I had a blast building this. Is it useful? Not really.Maybe instead of simulating a terminal you could use it to predict what you'd type next?So simulate _you_, not the terminal.
- ChanderGI was searching the blog but couldn't find details on the fine-tuning process. What was the hardware and software used? Any learnings there?
- OtherShrezzingI think this project is a very good way to explore the question:>What's the difference between a model that predicts intelligent output, and intelligence itself?It doesn't directly attack the question, but gives a neatly constrained thought experiment which you can see running.
- ameliusThe next step is training a model to pretend to be the internet.(You could run lynx in that terminal to train/test it without images)
- oilkillsbirdsVery cool. Fun project. I feel like there’s a wide field to be explored once you understand fine tuning good existing models
- __mpIt would be interesting to expose this on the internet. I wonder what the scrapers etc… would do with it.
- anonundefined
- sandGorgonthis is quite similar to amazon-science Cyber-Zero ?https://github.com/amazon-science/Cyber-Zerothe paper is quite interesting - https://arxiv.org/html/2508.00910v2
- wy1981Questions for folks familiar with fine-tuning: what are the best resources to learn fine tuning?
- air7I remember doing something like this in the ancient era of GPT 3 or 4. I just told it that it was a terminal responding to commands and it was surprisingly consistent.
- obilgicThere was a whole fake gui OS with similar concept right
- Muhammad523Why did it return -1 to 10 - 4
- ohadprVery 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.https://www.ohad.com/blog/voidware/
- LercI 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.
- psandorReminds 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...
- 4ggr0wonder if the PHP on this hallucinated terminal is patched already.
- yjftsjthsd-hWait, how did it `sleep 3`? I thought LLMs didn't have a concept of time
- thorumI 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?
- prodigycorpWow! 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?
- donperignonI 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.
- sudo_cowsayVerry Verrry Cool and neat!
- anonundefined
- teifererHaha nice!I'm a noob in this, could you enlighten me: what role does the base model play which you started with?
- anonundefined
- gobdovanJust gonna leave this here: https://en.wikipedia.org/wiki/Aggressive_mimicry
- vinaygundeti18[flagged]
- joka88xj[dead]
- wkilbride[flagged]
- luckystarr[dead]
- simedw[flagged]
- happybox2016[flagged]
- htoz1Where is the point of this project if i have terminal ?
- gitowiecBUG: Running in Firefox makes every keypress a slow motion show. It decodes every keypress instead of sending a command with Enter key