Hacker News: huydotnet

New comment by huydotnet in "Combustion engine web-based simulator"

huydotnet — Fri, 10 Jul 2026 20:06:36 +0000

If you're looking for a carefully crafted/written work to explain internal combustion engines, look no further than this one https://ciechanow.ski/internal-combustion-engine/ (the Mechanical Watch article from the same author was featured on HN a while ago).

New comment by huydotnet in "Show HN: Capacitor Alarm Clock"

huydotnet — Wed, 17 Jun 2026 23:16:21 +0000

For anyone jumping into this thread hoping to see capacitor use for timing, there is this blog post about something like that:

https://notes-huy-rocks.translate.goog/posts/diy-pomodoro-ti...

(google translate link because the original post was in Vietnamese)

New comment by huydotnet in "Running local models is good now"

huydotnet — Wed, 17 Jun 2026 14:45:10 +0000

One don’t have to buy a new computer to run Qwen3.6 or Qwen3.5 (35B A3B), given that they can already run Qwen3 30B A3B.

In fact with a 64GB mac, you can run pretty much all of the latest Qwen models.

Also, anyone who has been following local LLM are well aware that the quality and performance has become way way better since Qwen3.5

Show HN: Fixing grammar and spelling using on-device Apple Foundation Model

huydotnet — Tue, 16 Jun 2026 23:03:52 +0000

Article URL: https://github.com/huytd/afm-grammar/

Comments URL: https://news.ycombinator.com/item?id=48563489

Points: 3

# Comments: 0

New comment by huydotnet in "Running local models is good now"

huydotnet — Tue, 16 Jun 2026 16:47:57 +0000

I love that local LLMs are being discussed more often on HN recently. But for the post, I find it strange that the author claimed they were working with local models from day 1, but wrote a post that still links to Qwen2.5 and Qwen3 in mid June 2026.

New comment by huydotnet in "Mouseless – keyboard-driven control of macOS/Linux/Windows"

huydotnet — Fri, 05 Jun 2026 15:49:22 +0000

I've been building the same thing for a while https://github.com/huytd/octocmd It has everything you need to throw away the mouse: keyboard tab switching, search and click, vim-style clicking, keyboard scrolling.

New comment by huydotnet in "5x5 Pixel font for tiny screens"

huydotnet — Wed, 22 Apr 2026 20:32:08 +0000

I'm gonna use this article to explain to my peers about LLM quantization!

New comment by huydotnet in "Qwen3.6-35B-A3B: Agentic coding power, now open to all"

huydotnet — Thu, 16 Apr 2026 16:45:02 +0000

They are different quantization types, you can read more here https://huggingface.co/docs/hub/gguf#quantization-types

New comment by huydotnet in "Unsloth Studio"

huydotnet — Tue, 17 Mar 2026 22:20:49 +0000

you just answered your own question, "AI hobbyists who has 4090 at home". And they are pretty much targeted user of Unsloth since the start.

New comment by huydotnet in "Get Shit Done: A meta-prompting, context engineering and spec-driven dev system"

huydotnet — Tue, 17 Mar 2026 21:59:36 +0000

I've tried both. Each has pros and cons. Two things I don't like about superpowers is it writes all the codes into the implementation plan, at the plan step, then the subagents basically just rewrite these codes back to the files. And I have to ask Claude to create a progress.md file to track the progress if I want to work in multiple sessions. GSD pretty much solved these problems for me, but the down side of GSD is it takes too many turns to get something done.

New comment by huydotnet in "Ask HN: Programmable Watches with WiFi?"

huydotnet — Wed, 25 Feb 2026 00:54:34 +0000

Bangle is a good one https://banglejs.com/ Quite fun to work with. I got one from a conference, and my kid has been enjoying it a lot.

New comment by huydotnet in "Claude Code is being dumbed down?"

huydotnet — Wed, 11 Feb 2026 18:39:44 +0000

exactly what i think when reading the top of the article, maybe the author turned off vebose mode

New comment by huydotnet in "Railway (PaaS) global outage"

huydotnet — Wed, 11 Feb 2026 16:40:06 +0000

Joke about train line aside, I think Railway fits right in the spot that Heroku left.

They have a nice UI, support deploy any kind of backend-involved apps as long as it can be built into a docker container. While many PaaS out there seems to prioritize frontend only apps.

And they have a free plan, so people can just quickly deploy some POC before decide if it's good to move on.

Anyone know if there is any other PaaS that come with a low cost starter plan like this (a side from paying for a VPS)?

New comment by huydotnet in "Railway (PaaS) global outage"

huydotnet — Wed, 11 Feb 2026 16:27:18 +0000

Context: This is Railway the PaaS company, not your daily commute vehicle (which is good in general, still bad for many users, like me).

New comment by huydotnet in "Lessons learned shipping 500 units of my first hardware product"

huydotnet — Tue, 03 Feb 2026 23:19:09 +0000

> Due to a miscommunication with the factory, the injection pins were moved inside the heatsink fins, causing the cylindrical extrusions below.

What happened after this? the factory have to replace the casting mold at their own expense or you have to pay for it?

Use Your LM Studio Models in Claude Code

huydotnet — Fri, 30 Jan 2026 23:05:43 +0000

Article URL: https://lmstudio.ai/blog/claudecode

Comments URL: https://news.ycombinator.com/item?id=46831198

Points: 1

# Comments: 0

New comment by huydotnet in "LM Studio 0.4"

huydotnet — Fri, 30 Jan 2026 23:05:15 +0000

Well, to whoever downvoted my comment: It's supported now!!!! https://lmstudio.ai/blog/claudecode

New comment by huydotnet in "LM Studio 0.4"

huydotnet — Wed, 28 Jan 2026 20:54:31 +0000

yup, I've been using llama.cpp for that on my PC, but on my Mac I found some cases where MLX models work best. haven't tried MLX with llama.cpp, so not sure how that will work out (or if it's even supported yet).

New comment by huydotnet in "LM Studio 0.4"

huydotnet — Wed, 28 Jan 2026 19:47:39 +0000

I was hoping for the /v1/messages endpoint to use with Claude Code without any extra proxies :(

New comment by huydotnet in "Roam 50GB is now Roam 100GB"

huydotnet — Thu, 15 Jan 2026 17:26:39 +0000

I think this is one of the cases where strictly applying the guideline fails the reader, but yeah, I can see that this guideline make sense most of the (other) cases.