roger_
roger_ on Hacker News
Does this work with Qwen 3.8?
Paseo is great and has mobile notifications but it’s not as polished as omp web.
I guess “A” by itself would be a seperate token but my point is the model might be trying to say something that begins with that letter rather than actually answering.
You’d need to use an approach that links the output to a closed set.
> Answer with the letter of the best option only [A, B, C]
What if it says "D"? What if it tries to say "Additional details needed"?
(Also no calibration, etc.)
Does that break anything? Surprised it’s not the default.
Does installation still require root and a dedicated user account on Linux?
That really put me off.
Always wanted to implement that on a phone, it would be like a superpower!
My iPad is my primary computer so... me.
Thanks!
I’m looking for something that pushes portability without compromising too much core usability.
For example I can live without a touch screen if it means high quality physical buttons.
Surprised I never heard of this!
Looking to pick one up, any recommendations on X4 Pro vs Classic?
My computer's definitely gonna be faster after this.
~5000 chickens if anyone cares :(
Seeing a lot of these “run 1TB models with 1GB RAM” projects recently. Most seem vibe coded and probably won’t be maintained.
Hoping a winner emerges with some real momentum behind it.
I’m familiar with curve tracers but hadn’t heard about source measure units.
Don’t see any on eBay for dirt cheap, wonder what author paid (he said a fraction of retail).
Getting (further) into this myself so good timing. Running Qwen 3.6 27B at decent speed on some old cards but going to branch out.
I bough an Octominer for ~$150 which has power and PCIe slots and a basic Celeron and should let me expand to as many GPUs as I want.
I considered the P100s but I think the V100 16GBs are a better deal at $250. The 32GBs are way too much though.
That’s cool but 7 - 12 tps is frustrating for anything interactive.
Does this support Qwen 3.6 (e.g. 27B) and the myriad of llama.cpp options (batch sizes, quantization, etc.)?
I'd love to see some performance data.
Funny you mention that because the OMP GitHub issues (
https://github.com/can1357/oh-my-pi/issues) is almost exclusively attended to by a very efficient bot. I routinely submit issues and they’re replicated and resolved (via PRs) in ~30 mins.
To your question: it’s the difference between one person and an agent working on something vs an experienced dev and the entire community.
Time and tokens too of course.
Currently using Oh My Pi (
https://github.com/can1357/oh-my-pi) and appreciate the batteries included approach.
From my limited time using pure Pi, I found quite a few of the plugins lacking and had no desire to upgrade/fix and maintain them myself. I know others feel differently though.
I like the idea of keep Pi minimal but having “official”, high quality optional plugins to make it more usable.
Yeah I don’t think I could ever commit to a project like this and of this scale.
Might be different if it was something truly useful or novel vs a nerd snipe.
Very impressive that he pulled it off in a relatively short amount of time.
Definitely going to play around with this, thanks for posting.
I know MCMC isn’t your goal, but seems like this could be used for ABC-MCMC (as is?)
Would also be nice to have an option to plot using a KDE vs histograms.
(Also your FM example seems to be technically PM)
To monitor and instruct agents.
If there was a mobile app or at least some kind of agent agnostic telegram integration then I'd be more interested.
Hmm… how does one even pick between multiple vibe coded options?
I like to vet my options before committing to new software but who knows if the authors are gonna support these in a month? I don’t want to waste Fable tokens to fix bugs myself when they crop up.
This guy is behind the awesome Oh My Pi agent, so I’d give him a chance.
Anyone have experience switching from Docker to Podman?
I have a lot of compose files in my homelab/automation setup and those are what I’m most concerned about.
Has anyone tried this for LLMs and how does it compare to Vulkan?
How about Qwen3.6? What sort of prefill/decode rates?
Edit: 3.6 not 3.7!