Live data from Hacker News

Viewing profile — winstonp

winstonp

HN member
Joined
Wed, Oct 04, 2023, 7:15 PM UTC
HN karma
128
Public activity
53 items

About winstonp

No profile information was provided.

Recent public activity

  1. comment
    Comment #49090758

    16 tokens / s is not nothing.

  2. comment
    Comment #48997969

    Apple isn't counting on their model to be a frontier coding and cowork model. Gemini is perfectly fine for the tasks that new Siri is supposed to be doing.

  3. comment
    Comment #48893580

    That is not the Grok CLI being discussed. That's an open source, third party CLI. https://x.ai/cli is the official Grok CLI being discussed, and it is not open source.

  4. comment
    Comment #48846866

    The avg coding session has hundreds or thousands of tool calls. Even a 5% failure rate noticeably notches up token use and cost. See Gemini.

  5. comment
    Comment #48845784

    Doubt. Tried it, Grok 4.5 is leaps and bounds ahead of Gemini for real work. And token costs vs. raw compute+electric cost is unit profitable too.

  6. comment
    Comment #48796492

    While I mostly agree with your post, I do want to point out one thing: > Or he could release a model trained largely by existing open weights models. Which without some huge breakt…

  7. comment
    Comment #48737941

    same happened to Opus 4.7

  8. comment
    Comment #48653489

    the British are notoriously sensitive to heat. They'll call 30 Celsius weather a heat wave.

  9. comment
    Comment #48590735

    do we think he found it on craigslist

  10. comment
    Comment #48588834

    Gemini pretty clearly has the best underlying model, and the worst RL and post-training of the lot.

  11. comment
    Comment #48577945

    It is ridiculous to be building infrastructure with a seventy five year lifespan under an assumption that may never come in its entire life.

  12. comment
    Comment #48576448

    Car apps, beside Tesla, are universally awful to use. Even Tesla's is not beyond reproach (app size is massive, for one), but at least it doesn't make me want to poke my eyes out. …

  13. comment
    Comment #48575955

    They are absolutely clueless about how to talk to this administration.

  14. comment
    Comment #48560349

    CC TUI is often a culprit of memory leaks, image-pasting is a nightmare, particularly over SSH, flickering all over the UI, among others.

  15. comment
    Comment #48559262

    You can! You just have to pay API prices.

  16. comment
    Comment #48559251

    google models are still very unreliable at actually calling the tools you want it to call.

  17. comment
    Comment #48558792

    I don't believe Anthropic trains on Trainium, only serves models on it.

  18. comment
    Comment #48494160

    Claude Code TUI is garbage. There's nothing worth protecting in there.

  19. comment
    Comment #48481557

    I do think Anthropic nailed their naming down much better than OpenAI

  20. comment
    Comment #48466839

    OpenAI's training is better suited to developing models that don't have these tendencies

  21. comment
    Comment #48327923

    I've never had a smelly Mac, and I've owned maybe 10 different ones across personal and various work laptops. And 90% of devs I've ever met have used Macs and none of them smell ei…

  22. comment
    Comment #48314052

    Google Search has been awful for the last couple of years. Good riddance to SEO.

  23. comment
    Comment #48115605

    Same. Overuse of the word "genuinely" is another tell.

  24. comment
    Comment #47771767

    [flagged]

  25. comment
    Comment #47657127

    Which apps have you seen ask for someone to setup a local LLM? Can't recall having ever seen one