This article is very brief and not deep enough. There is one I’m finding a much more “to the bone” and explaining io_uring concepts in much deeper details:

https://unixism.net/loti/index.html

Feel free to reverse-search the related HN thread too.

Thank you

In (post)communist countries there is a common name - ISOSTAT switch.

Not yet, but soon… Bun

You could keep multimodal projector (understanding of audio, images & PDFs) in system RAM with `--no-mmproj-offload` in llama.cpp. Of course, then it is not accelerated with GPU, but you save its VRAM.

Interesting, I might try that, thanks!

That is why we have discussions like these: https://x.com/i/status/2039099810943304073

X is the worst place to hold community discussions.

The official SW on MacOS is somewhat usable if:

- you disable all communication with a firewall (so it doesn't autoupdate)

- `sudo pkill -9 LogiPluginService && sudo rm -rf /Applications/Utilities/LogiPluginService.app` (so it does not eat resources and don't run a useless service in the bg)

"I'm sorry, my knowledge cuttoff is 1875"

Start with the YT series on neural nets and LLMs from 3blue1brown

The most funny thing is how synchronicity worked its magic:

Roo Code experimental code indexing using vector DB dropped 3 days ago. Theire using Tree-sitter (the same as Aider) to parse sources into ASTs and do vector embedding on that product, instead of plaintext.

https://news.ycombinator.com/item?id=44117455

Yeah, I remember that option - basic tier of DTU DB with 250GB of storage - free for one year, then continue for $15/m.

When the client brought some 3rd party expert and he advised rewriting to MySQL, I quickly did the math and it was like $60/m, without a free year.

We continued with DTU MSSQL with Prisma ORM and never regreted.