[simonw]

Sure, but the problem is when you take that half hour of work and share it with other people without making clear how much effort has gone into it.

Software is valuable if it has been tested and exercised properly by other people. I don't care if you vide coded it provided you then put the real work in to verify that it actually works correctly - and then include the proof that you've done that when you start widely sharing it with the world.

Right now it's impossible to tell which of these projects implementing the paper are worth spending time with.

[kristjansson]

> without making clear how much effort has gone into it

I'm increasingly convinced this is the critical context for sharing LLM outputs with other people. The robots can inflate any old thought into dozens of pages of docs, thousands of lines of MR. That might be great! But it completely severs the connection between the form of a work and the author's assessment/investment/attachment/belief in it. That's something one's audience might like to know!

[dalemhurley]

Is t the point of an MVP to be an MVP?

The OP put together a POC and shared it, showing novel concepts used together. They are not some large R&D lab.

The purist tests being asked for is in contradiction to the ShowHN guidelines.

[aegis_camera]

Thanks, we are not large R&D lab, limited resources. We were working on a product with is a Local VLM first BYOD when you want Video Security application, our users requested to have a MLX backend benchmark comparison, we tried hard to not deliver with Python in the application bundle, so we searched for a pure binary based MLX implementation the results shown we need to build one. It took us two weeks to get it working and we had been testing with multiple models. As a reference, you can see the result here: https://www.sharpai.org/benchmark/

Then we saw the announcement from Google about TurboQuant, it's so cool, so we started to integrate them (along with SSD/Flash streaming). It's a non-trivial process and thanks for your support and understanding. When we saw the mobile application alive with QWEN 3 1.7B model, we thought it worth.

If we get anything similar with well maintains, we will definitely adopt it since our target is the production delivery, if this one gets good support from the community, we will continue to support.

I think all the posts here gave us a reason to continue.

[Aurornis]

> The OP put together a POC and shared it, showing novel concepts used together.

That's the contention: There are countless POCs for these concepts already, and some of them were used as the basis for this project.

It's not really a novel POC, it's the result of putting the previous work into Claude Code and telling it to rewrite it in Swift, then putting your name on it. To be fair, the person did start adding the reference projects to the very end of the README

But if you didn't what to look for, you'd assume this was a very novel project attributable to their own work

[simonw]

This post wasn't marked as a Show HN.

[aegis_camera]

Tried, but wrong time to post, it got zero attention . :)