HN user

umtksa

44 karma

https://studiomoi.co

Posts4
Comments89
View on HN

I know this isn’t a question, but more of a general observation about LMs. However, I’d still like to say that a fine-tuned Qwen3 0.6B model can produce more effective and faster results than a raw Gemma 3 12B model. Maybe it’s because I’m not a programmer, but I believe being able to give commands in natural language adds a great deal of flexibility to software.

blenderq --blend /path/to/file1.blend /path/to/file2.blend love this option

normaly I just use blender -b path/file1 -a && blender -b path/file2 -a

thank you for making this I did not read your code and I'm curious about where did you get (or calculate) the progress value, thank you for making this

most of the people I know use WhatsApp and Telegram because they can read their notes from any device/ant time and can forward it any one. so for this use case ideabook cannot do what WhatsApp or Telegram do for me. But I like the clean interface. note: mobile appstore links are not there

I'm running a dashboard on an old samsung phone for crawling some sites and displaying them in an easy to read format.

Copy any request you made on chrome dev tools as curl convert curl to a function node. If anything breaks on site side just make a new curl and copy thoose values.

interesting portfolio, but for me it's just something like a GPT mockup with clickable questions.

As a user facing your frontend I'm not getting any benefit from LLMs.

The first readable data about you takes more than 8 seconds. And I cannot ask any question. With this abilities it's like a poor implemented QnA page.

Hope I made my point clear. I'm not a coder and yes I see GH page of your project

I love their components page and modular system. With article components any one can create a clean, responsible blog or landing pages. As a non profesional it's a perfects system for me.