Live data from Hacker News

Viewing profile — kirurik

kirurik

HN member
Joined
Tue, Aug 26, 2025, 9:54 AM UTC
HN karma
8
Public activity
16 items

About kirurik

Keeping on keeping on. Here to soak up the daily knowledge.

All comments and mistakes are my own.

GitHub: https://github.com/Kena-Njonge Substack: https://substack.com/@kena540200

Recent public activity

  1. comment
    Comment #46632508

    You can run some models pretty decently using CPU inference only, things like Gemma 3 that are built for exactly that use case or some tiny speech to text models via llama.cpp that…

  2. comment
    Comment #46632421

    Thank you for replying to me and recommending a feature - that I didnt know about!

  3. comment
    Comment #46486579

    Saving this

  4. comment
    Comment #45723595

    I agree, I think there is such a thing as AI overuse, but I would rather someone uses AI to form their points more succinctly than for them to write something that I can't understa…

  5. comment
    Comment #45723477

    To be fair, you are assuming that the input wasn't garbage to begin with. Maybe you only notice it because it is obvious. Just like someone would only notice machine translation if…

  6. story
    Show HN: Osync – A Git and rsync tool for local syncing and backups

    Hey everyone, I made a small tool called osync, a setup that uses Git and rsync to sync and back up directories between devices. It started as a personal experiment to sync my Obsi…

  7. comment
    Comment #45611894

    True, it is meaningless how good one is at vimgolf if it doesn't flow naturally

  8. comment
    Comment #45519991

    I did the neovim tutorial which I accessed via :Tutor, I see now that vimtutor has some divergences, I will do that tutorial also, to improve my muscle memory and knowledge. Thanks…

  9. comment
    Comment #45518574

    I'm currently learning vim and usign neovim, coming from VScode, wondering how y'all learned it if you made a similar switch, how long it took to learn and your opinions on purely …

  10. story
  11. comment
    Comment #45139686

    It seems obvious, but I hadn't thought about it like that yet, I just assumed that the LLM was finetuned to be overly optimistic about any user input. Very elucidating.

  12. comment
    Comment #45078466

    True, and many not so intelligent people may overestimate their intelligence and do it. So maybe it does somehow end up being representative.

  13. comment
    Comment #45077711

    The self-selection bias is definitely something to consider. I’d guess people who feel relatively confident in their intelligence are more likely to take the test.

  14. story
  15. comment
    Comment #45049173

    There definitely is an element of shooting oneself in ones own foot, but sometimes it seems unavoidable to me, or the effort just isn't worth it e.g. if I am using sklearn or numpy…

  16. comment
    Comment #45024452

    I am not an experienced programmer, but I liked python because of the dynamic typing, but tbh no type hints are a nightmare (as I used to use python). These days I gravitate toward…