Live data from Hacker News

Viewing profile — polyrand

polyrand

HN member
Joined
Mon, Mar 16, 2020, 12:10 AM UTC
HN karma
4,283
Public activity
412 items

About polyrand

Medical doctor and machine learning/software engineer.

ricardoanderegg.com

Twitter: [at] ricardoanderegg Contact: hn [at] polyrand [dot] net

Recent public activity

  1. comment
    Comment #48938525

    I'm already quite excited about Turso being SQLite-compatible, but adding many features on top. And when a feature is not directly compatible with SQLite (ie: you can't directly re…

  2. story
  3. story
  4. comment
    Comment #48852373

    On one hand, this had to happen at some point. I feel the split between ChatGPT vs. Codex wasn't helping OpenAI. Anthropic did it right from the beginning by unifying everything in…

  5. story
  6. comment
    Comment #48558775

    I believe that's like saying we should only have a single "throw" event in athletics. Or why having hurdles events when you already have regular running ones. I like that we can ha…

  7. comment
    Comment #48558002

    Finswimming is actually a separate sport, just not an olympic sport. Although it has some exciting characteristics like very fast 50 meter races, which I enjoy as a "regular" (non-…

  8. story
  9. story
  10. comment
    Comment #47253946

    I find this a very exciting release. I was actually hoping we would somehow get macOS on mobile 'A' chips some day. And I think this is better than putting 'M' chips on an iPad. My…

  11. story
  12. comment
    Comment #46925245

    I do this, and it's a huge quality of life improvement. No so much because of shadowing existing binaries, but for better command auto-complete. For example: I have a bunch of tmux…

  13. comment
    Comment #46905979

    > a period of inefficiency I think this is something people ignore, and is significant. The only way to get good at coding with LLMs is actually trying to do it. Even if it's ineff…

  14. comment
  15. story
  16. comment
    Comment #46763925

    I share the same feeling. I waited as much as possible to upgrade to iOS 26 / macOS Tahoe. Two days ago, I finally upgraded. Liquid Glass is one of the worst things I've ever seen …

  17. comment
    Comment #46747694

    Don't forget that if you're using SQLite on something like EBS, multiple queries may not be efficient. I'm saying this as a huge SQLite fan, but also beware of what kind of storage…

  18. story
  19. story
  20. comment
    Comment #46682173

    I've been using z.ai models through their coding plan (incredible price/performance ratio), and since GLM-4.7 I'm even more confident with the results it gives me. I use it both wi…

  21. story
  22. comment
    Comment #46376653

    Not sure about the impact of these, I guess it depends on the context where this engine is used. But there seems to be already exploits for the engine: https://x.com/itszn13/status…

  23. comment
    Comment #46362891

    That's interesting, thanks for sharing! It's a pattern I saw more often with claude code, at least in terms of how frequently it says it (much improved now). But it's true that jus…

  24. comment
    Comment #46359927

    A few comments mentioning distillation. If you use claude-code with the z.ai coding plan, I think it quickly becomes obvious they did train on other models. Even the "you're absolu…

  25. story