Hacker News: npodbielski

New comment by npodbielski in "Qwen 3.8 27B is excellent, but it defaults to overthinking things"

npodbielski — Mon, 17 Aug 2026 04:57:01 +0000

It is. I am running it on R9700

New comment by npodbielski in "Qwen 3.8 27B is excellent, but it defaults to overthinking things"

npodbielski — Mon, 17 Aug 2026 04:54:24 +0000

On the other hand I am running this model to write some tests for my hobby project for two days now and it is able to deduce and fix errors and bugs that Qwen 3.6 was not able to. Yes, it thinks a lot but this makes reasoning about problem much better. Also it did not run it self into a loop once even which is a problem with Q4 even with dense models.

On the other hand it maybe do too much i.e. I asked "how we could test it?" and instead of answering it just actually wrote tests. But it was the same with Qwen 3.6.

New comment by npodbielski in "[dead]"

npodbielski — Sun, 16 Aug 2026 13:28:38 +0000

This is not true. As author points out his domain is invalid unless you install something. So the whole thing is misleading.

New comment by npodbielski in "Pixel 11 Pro Fold"

npodbielski — Thu, 13 Aug 2026 02:38:01 +0000

What a terrible website to open on your phone. Text and image is clipped, it jumps up and down, loads for several seconds, refreshes entire page several times... I opened it and have no idea what this hardware supposed tonbe.

New comment by npodbielski in "Show HN: Ante, a coding agent in a single binary that runs offline"

npodbielski — Tue, 11 Aug 2026 12:20:35 +0000

so it is just llamafile with few additional application in bundle?

New comment by npodbielski in "That time when I failed the Microsoft interview"

npodbielski — Tue, 04 Aug 2026 08:29:04 +0000

Yes, the best way to land yourself a good gig is to have a friend in the company already and will put a good word.

New comment by npodbielski in "Qwen3.8-Max: A New Bar for Coding and Cowork"

npodbielski — Mon, 03 Aug 2026 05:49:08 +0000

In my case I would say they are comparable but moe models are looping and getting lost a lot more than dense models.

On the other hand having 90t/s with any local model is nice and Pi with loop police extension can prevent looping a lot.

New comment by npodbielski in "Elevators"

npodbielski — Sat, 01 Aug 2026 08:00:07 +0000

How people do such nice animation? Is there is some nice program you can use? I looked and I could not find anything that seemed really easy to use. Llms can sometimes generate something usefull and sometimes something attrocious. I remember few months back article where someone create animation of how 3.5" 1.4MB disk is build, somebody asked about this in the comment and author said it was done mostly by hand. While this is impressive it would be cool to be able to draw some animation for work prestnation that looks nice but also so I do not have to spend 3 days crafting something like that. Would be nice to draw few of them in my blog too. Any recommendations?

New comment by npodbielski in "Superlogical"

npodbielski — Thu, 30 Jul 2026 04:42:40 +0000

And it is fun!

New comment by npodbielski in "Una GPS smart watch – Repairable, USB-C charging, developer-friendly"

npodbielski — Wed, 29 Jul 2026 09:21:57 +0000

Anybody have good recommendation of a watch that you can write your own apps for?

New comment by npodbielski in "Our position on open-weights models"

npodbielski — Tue, 28 Jul 2026 13:33:24 +0000

Yeah makes everyone agree on banning Chinese models and then force them to use mine models. How I could misunderstand *that*.

New comment by npodbielski in "Show HN: Reverse Minesweeper"

npodbielski — Mon, 27 Jul 2026 12:07:15 +0000

very addictive :) thanks!

New comment by npodbielski in "Show HN: CheapSecurity – Lightweight, Self-Hosted CCTV for Linux SBCs"

npodbielski — Sun, 26 Jul 2026 17:18:10 +0000

I always wonder why author of such software will not add some screenshot or gif showing UI and how it does work? In features there is mention of web interface.

New comment by npodbielski in "Running a 28.9M parameter LLM on an $8 microcontroller"

npodbielski — Sun, 26 Jul 2026 10:35:44 +0000

Rig with 6x RTX 5090. I would not say it is RAM only

New comment by npodbielski in "Politician reads AI prompt during assembly"

npodbielski — Sat, 25 Jul 2026 17:15:38 +0000

Policy influence idea: find out who are the assistants of policians and what ai assistant, subscription they use and give them different answers than to everyone else. You do not have to even corrupt them.

New comment by npodbielski in "Hetzner is working on LLM Inference"

npodbielski — Fri, 24 Jul 2026 14:41:46 +0000

No Qwen 3.6? Why?

New comment by npodbielski in "Startup founders urge U.S. government not to shut off Chinese open weight AI"

npodbielski — Thu, 23 Jul 2026 18:19:13 +0000

ah that makes sense now! I must be tired...

New comment by npodbielski in "Startup founders urge U.S. government not to shut off Chinese open weight AI"

npodbielski — Thu, 23 Jul 2026 15:49:25 +0000

So Y Combinator signed it too? But this is HN, Y combinator website. I think I am missing something because I never read any opinion like 'we should ban Chinese models'.

New comment by npodbielski in "Show HN: 18 Words"

npodbielski — Fri, 10 Jul 2026 13:51:46 +0000

Really hard game for someone that is non native. Or maybe I am just at scrabbles?

New comment by npodbielski in "Chatto is now open source"

npodbielski — Thu, 09 Jul 2026 07:16:30 +0000

Sure I understand though, I have honestly no idea what tauri is really. Sure there is a link and it looks like some kind of web framework. Looks nice but it is hard to picture how chat application written with that would look like. I am not trying to force you to do want I want. I just think it is in a good taste to put some screenshots or even a gif. But I understand your reluctance.