• 1 Post
  • 13 Comments
Joined 3 years ago
cake
Cake day: June 29th, 2023

help-circle

  • Get llama.cpp and try Qwen3.6-35B-A3B. Just came out and looks good. You’ll have to look into optimal settings, as it’s a Mixture of Experts (MoE) model with only 3B parameters active. That means that the rest can stay in RAM for quick inference.

    You could also try the dense model (Qwen3.5-27B), but that will be significantly slower. Put these in a coding harness like Oh-My-Pi, OpenCode, etc. and see how it fares for your tasks. Should be ok for small tasks, but don’t expect Opus / Sonnet 4.6 quality, more like better than Haiku.


  • Even with the Zero Knowledge approach, you will still run an app on a phone (what if I don’t have one) that will make some call to the government’s servers, which will most likely know what website you’re trying to access. We’re moving the data mining from some third party to the government, which can be wrongly used later if some idiot comes into power. If it’s not making a call to a government’s servers, I would be surprised, since you could imagine someone just bypassing this to always return “Over 18”.

    Even funnier (read “sad”), this initiative will probably rely on Google and Apple to keep it robust, and will likely have no availability on rooted phones or non-Google Play Services ones. It’s premature at best to deploy this in a meaningfully safe way.




  • You’re right! Sorry for the typo. The older nomic-embed-text model is often used in examples, but granite-embedding is a more recent one and smaller for English-only text (30M parameters). If your use case is multi-language, they also offer a bigger one (278M parameters) that can handle English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, Chinese (Simplified). I would test them out a bit to see what works best for you.

    Furthermore, if you’re not dependent on MariaDB for something else in your system, there are also some other vector databases I would recommend. Qdrant also works quite well, and you can integrate it pretty easily in something like LangChain. It really depends on how much you want to push your RAG workflow, but let me know if you have any other questions.



  • For notes, I have moved to Joplin with the option to synchronize my data using a WebDAV server. It works really well, and it has both a mobile and desktop app. If you’re interested in developing your project, maybe you can have a look at the options this provides. For example, I really like the ability to separate notes between groups, assign tags, create drawings, and the possibility to use Markdown.

    Good luck with your projects! To mirror @enemenemu’s suggestion, I would also look into collaborating with the people trying to push the EU Docs alternative. Not sure if that will work, but it’s worth a shot if you’re interested :D



  • I also had to upload 2000 photos. The issue was that they had to encrypt each, which took me like 2 days with it running in the background 😅 It could have also been due to my phone being quite old. I don’t rely on it that much, other than using it as an off-site back-up for my most important documents.

    I do agree that the best choice is a self-hosted solution with proper security, but sadly not everyone has the time or the skills to manage that. The Proton CEO thing also annoyed me, but the Proton Foundation as a whole has good opinions about privacy (e.g., against chat control proposal in the EU). However, next time a slip like this happens from them, I’ll probably have had enough time to move my stuff to a local deployment.




  • Piracy. I’d buy albums if I had money, though. I’ll slowly phase into getting them once I get some more cash.

    I can find most stuff I listen to, and I rarely grow my music library. I mostly listen to 20-30 albums, with some more mainstream music peppered in.

    My music library currently sits at 90 gigabytes (mostly flacs), so quite small compared to others I’ve seen around here. Still, I have plenty of variation to keep me entertained :D

    If you have Tidal, aren’t there some apps to rip the lossless audio from there? You could get most of the stuff that you need, and then cancel the subscription. If you feel bad, maybe order some merch from the band, haha.