Live data from Hacker News

Viewing profile — sonnig

sonnig

HN member
Joined
Fri, Sep 22, 2023, 11:44 AM UTC
HN karma
65
Public activity
22 items

About sonnig

No profile information was provided.

Recent public activity

  1. comment
    Comment #46730965

    I've owned iOS devices since around 2010 I think, and one of the first things I do when setting them up is disable autocorrect and most other typing assistances. For this reason! A…

  2. comment
    Comment #46716620

    Yep, it's similar in that way, but not in a imageboard/discussion context

  3. comment
    Comment #46696769

    Yeah me too

  4. comment
    Comment #46685841

    Apologies for that, I have removed it.

  5. comment
    Comment #46684979

    I've changed this now, thanks for the feedback

  6. comment
    Comment #46684193

    i agree removing punctuation wouldve been a good idea alas it may be a bit too late since that would modify the hash of previous inputs in the future hmm but i will think about it

  7. comment
    Comment #46684143

    Me too, and other 16 users

  8. comment
    Comment #46684099

    True! That would be a more powerful approach. Here I kept it quite basic since I was not very familiar with the tooling. I do apply lowercasing of text + some whitespace stripping …

  9. story
    Show HN: Subth.ink – write something and see how many others wrote the same

    Hey HN, this is a small Haskell learning project that I wanted to share. It's just a website where you can see how many people write the exact same text as you (thought it was a fu…

  10. comment
    Comment #46681656

    Assuming both agents are using the same model, what could the reviewer agent add of value to the agent writing the code? It feels like "thinking mode" but with extra steps, and mor…

  11. comment
    Comment #46678995

    Well put. I can't help thinking of this every time I see the 854594th "agent coordination framework" in GitHub. They all look strangely similar, are obviously themselves vibe-coded…

  12. comment
    Comment #46542404

    I am working with kilo-stock-tokens. Currently producing 3000 LoC/h (trying to ramp up to 6000 by the end of the week). I have also deployed 4 union-busting agents in case the othe…

  13. comment
    Comment #46541206

    I searched for "poke push notification framework" on Kagi. But even then it was hard to find.

  14. comment
    Comment #46541154

    Mind sharing your workflow? I'm at 24.3x productivity right now, 5 parallel agents, 2 monitoring Opus agents, 1 architect agent and 2 Senior QA agents, each with independent memory…

  15. comment
    Comment #46519657

    It makes me so exhausted trying to read them... my brain can tell immediately when there's so much redundant information that it just starts shutting itself off.

  16. comment
    Comment #46493112

    Maybe [1]? Sounds like ntfy.sh, but more… AI [1] https://poke.com/docs/developers/api/message-poke

  17. comment
    Comment #46480926

    I think the same. It sounds quite more practical to have LLMs code in languages whose compilers provide as much compile-time guardrails as possible (Rust, Haskell?). Ironically in …

  18. comment
    Comment #45833122

    I strongly recommend the book "Mastering Emacs" by Mickey P. You will need some patience as well, I recommend going slow and steady for a week at least using the book, with a vanil…

  19. comment
    Comment #45603784

    This conversation reminds me a bit of https://news.ycombinator.com/item?id=21191676 some time ago (similar misuse of the term "open source")

  20. comment
    Comment #45567148

    Looks great!

  21. comment
    Comment #45527375

    we've integrated granian into our stack at $WORK recently and couldn't be happier

  22. comment
    Comment #45489293

    Are many HN members in Zürich? I was suprised to see this type of news with so many points, though it's quite amusing to see the mixture of different topics in the front page.