Live data from Hacker News

Viewing profile — tmzt

tmzt

HN member
Joined
Sat, Mar 12, 2011, 10:36 PM UTC
HN karma
788
Public activity
772 items

About tmzt

Building @GetPersonalOS email info@chitin.sh Github github.com/tmzt X: @tmztmobile

Recent public activity

  1. comment
    Comment #49211523

    If you're looking for way to get userdebug functionality without building a huge source tree, I created regraph[0]. It's similar to other solutions but does not inject sudo or root…

  2. comment
    Comment #49205732

    A nice little asciinema demo would be helpful on the TUI page. I should be able to see what it is, how it presents the contained agents, etc. I've been evaluating a few of these (a…

  3. comment
    Comment #49160748

    Are there any with small system prompts that are still useful, especially with local models and subagents?

  4. comment
    Comment #49141578

    Of course, both of those examples started out as proprietary software. [1] https://www.blender.org/about/history/ [2] https://www.libreoffice.org/libreoffice-timeline/

  5. comment
    Comment #49141260

    This should be a Show HN but looks incredibly interesting and definitely on-topic for the HN crowd. The historical project it references isn't widely known either. To the author: y…

  6. comment
    Comment #49033566

    Anybody know what happened to the Pattern Language Wiki? I haven't been able to find it on archive.org or anywhere else. It might have been twiki or similar if not mediawiki softwa…

  7. comment
    Comment #48999764

    A prehensile-tailed monkey? Watch them perform simple tasks with three useful appendages. (Really five)

  8. comment
    Comment #48982405

    The 40-bit hashed address seemed familiar, then I realized that I (and Claude) had used a similar concept in a VM we built for the OS I've been building. It's a capability and typi…

  9. comment
    Comment #48964867

    I went ahead and forked this and added a new remote INFER protocol. You can see it at https://github.com/tmzt/ds4 if interested.

  10. comment
    Comment #48956066

    This looks useful for somebody with a 16-32GB Mac Mini interested in running larger MoE models. I've been working on a mesh environment that relies on an explicit prefix hash in th…

  11. comment
    Comment #48943509

    Awesome. I'd love to see this evolve into something, maybe a Matrix server of our own. For now, I've been hanging out here as tmztmobile: https://matrix.to/#/#pocket-bootloaders:sa…

  12. comment
    Comment #48942435

    Updated and added links to gsmarena, thanks for that.

  13. comment
    Comment #48939808

    Thanks. I will.

  14. comment
    Comment #48937503

    I pushed all the intermediate branches as well.

  15. story
    Show HN: A modern port of Linux to a ten-year-old QWERTY phone

    I ported modern Linux to a ten-year-old HTC QWERTY phone as a handheld terminal. I wrote it up here: https://tmzt.github.io/blog/a-modern-port-of-linux-to-a-ten-... You can see the…

  16. comment
    Comment #48835767

    So you've heard of USB?

  17. comment
    Comment #48690447

    You can with the newer instances that suport nested VM. There was a recent story about this here https://news.ycombinator.com/item?id=48556561 .

  18. comment
    Comment #48658246

    Personally, I'm repurposing an older HTC phone with slide-out keyboard (the Speedy) with a new Linux port.

  19. comment
    Comment #48588092

    Do you see much of a difference between started Chromium instances with the same configuration in terms of the contents of allocated memory? Are they deterministic? If not, could y…

  20. comment
    Comment #48543793

    I've been working on a mesh network for private AI models running remotely, controlled by mobile devices (smartphones, tablets, etc.). The mesh is constructed like a piconet, a few…

  21. comment
    Comment #48351188

    I thought they were itenerant troubadours.

  22. comment
    Comment #48326909

    Sounds a bit like Transmeta Crusoe.

  23. comment
    Comment #48240554

    Same. I switched my efforts to a larger Gemma 4 MoE model (26B-A4B) and llama.cpp and started getting meaningful results. I also implemented subagents for querying, determining whi…

  24. comment
    Comment #48240468

    It's basically restricting what logits are allowed when sampling the model to conform with the JSON (or whatever) shape. It can also cause the model to get "confused" though and do…

  25. comment
    Comment #48070492

    Doing the same for Apple M-series with fused wgsl shaders specifically targeting Qwen3/3.5. My effort is called shady-thinker and is on github at github.com/tmzt/shady-thinker. Thi…