Hacker News: aziis98

New comment by aziis98 in "Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning"

aziis98 — Thu, 16 Jul 2026 23:32:33 +0000

When for the training part you have to consider brains had like billions of years to develop. Maybe one of the reasons llms seem to be so expensive to train is because we are "compressing" in far less time that learning part

New comment by aziis98 in "Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPU"

aziis98 — Wed, 15 Jul 2026 18:01:01 +0000

For me, at least for agentic use, you need at least ~40tps. Less might be good only for tasks you could run in the background (like at night maybe).

Instead of coding agents like tool for local models I would like to see more "docker ps" like tools where you can queue up tasks that get processes incrementally (maybe when the pc i idle) and are specialized for doing retries and caching as much work as possible to work decently with slow local models.

New comment by aziis98 in "Show HN: I mapped 8.5M research papers into an interactive atlas"

aziis98 — Thu, 09 Jul 2026 21:06:26 +0000

I also made my own variant recently. I really liked the idea of litmaps but I didn't really like the UI/UX or "graph expand" feature (it uses some internal heuristic that is not very clear).

https://paper-explorer.aziis98.com/ (also on github https://github.com/aziis98/paper-explorer)

This uses OpenAlex as a source of articles and to let you explore the citation graph of papers. This is still a prototype mostly made to test out how far I could go with vibecoding (well I still checked the code now and then) something without a js framework. Someday I think I will add more features to it, but now there is already a somewhat working version of import/export so I'm fine with it.

New comment by aziis98 in "Ternlight – 7 MB embedding model that runs in browser (WASM)"

aziis98 — Tue, 07 Jul 2026 10:44:48 +0000

This would be nice as an Astro (or generic meta-framework plugin) that automatically parses all generated html files and generates a small db of embeddings.

This way on the frontend you can lazily load this. Maybe you could even store the HNSW in chunks and just load the pieces you need for your specific search query.

i.e. like https://pagefind.app/ but to get fully static vector search.

New comment by aziis98 in "ZCode – Harness for GLM-5.2"

aziis98 — Wed, 01 Jul 2026 19:36:26 +0000

Is this GUI only?

New comment by aziis98 in "A native graphical shell for SSH"

aziis98 — Mon, 29 Jun 2026 23:00:58 +0000

Love it!

I also did some experiments some time ago. The thing this is missing for me is the ability to also run arbitrary commands other that just using a few premade apps. In fact I think this stuff becomes really interesting when you put a real "shell" on top of this.

And I don't mean a classical posix shell, something that can be used to leverage the full power of the custom ui and frontend. Also a must have is "nestable connections".

The experiment I was doing was with a web interface and a statically compiled Go backend (for easy deployment via ssh). Maybe some day I will finish it xD

New comment by aziis98 in "Show HN: TikZ Editor – WYSIWYG editor for figures in LaTeX"

aziis98 — Tue, 23 Jun 2026 21:19:44 +0000

Wow, awesome project! I gave a look a bit at the code (before realizing this was made with coding agents as said below on the website) and this seems really well made.

Still, I would really like to know how you approached this from an architecture perspective. I'm also curious to how much coding agents structured the code like so by themselves or if you had to steer them heavily (I've just tried a bit gemini flash from antigravity cli so I'm a bit behind on this).

Also how did you approach the rendering correspondence with actual tikz code? Do you have some tests that like render the tikz using latex and your js pipeline and compare the result for differences?

Introducing HRM-Text

aziis98 — Sun, 24 May 2026 21:15:46 +0000

Article URL: https://sapient.inc/introducing-hrm-text/

Comments URL: https://news.ycombinator.com/item?id=48261064

Points: 2

# Comments: 0

New comment by aziis98 in "LFM2-24B-A2B: Scaling Up the LFM2 Architecture"

aziis98 — Sat, 02 May 2026 14:08:14 +0000

> I was able to get I think 20 or 30 tokens per second on CPU (DDR4 ram) alone

What are you using for inference? I have a recent intel laptop with 32GB of DDR5 and I am getting at most 25tps with the llama cpp vulkan backend (that is the fastest, I also tried sycl but it is a bit slower)

New comment by aziis98 in "LFM2-24B-A2B: Scaling Up the LFM2 Architecture"

aziis98 — Sat, 02 May 2026 13:54:22 +0000

I just tried the Q4_K_M variant of this [] and this is one of the first models that run at ~20tps on my laptop. I also tried it with some "hard" maths questions and it clearly knows much. Can't wait to try some local coding agent harnesses with it (I recently discovered kon [1] and dirac [2] and wanted to try them out)

The only thing I'm not sure about is if this model supports thinking or not.

[1]: https://github.com/0xku/kon

[2]: https://github.com/dirac-run/dirac

New comment by aziis98 in "Boss-CSS: I created another "CSS-in-JS" lib"

aziis98 — Mon, 02 Mar 2026 23:04:04 +0000

I also did some experiments in this space as I have the same complaints about Tailwind

https://github.com/aziis98/preact-css-extract

I made this as I couldn't stand writing another 2K lines css file and wanted to try the atomic css wagon without having to switch from preact or having to learn tailwind