Live data from Hacker News

Viewing profile — potatoman22

potatoman22

HN member
Joined
Wed, Nov 04, 2020, 3:24 PM UTC
HN karma
797
Public activity
521 items

About potatoman22

No profile information was provided.

Recent public activity

  1. comment
    Comment #48600254

    It's not specific to SQLlite per se, but that's what most dashboard builders are

  2. comment
    Comment #48581023

    I was trying to say there's precedent for using ML in this field. I don't think they even said this product is an image generation model. It's probably some ML version of this http…

  3. comment
    Comment #48579898

    Generative models have been used in healthcare for a while for things like drug design and data generation. Not to mention all the algorithms (and probably ML) used in generating r…

  4. comment
    Comment #48451304

    I'd wager that for 99.9% of "Apple Intelligence" tasks, Google's models perform just as well as other frontier labs. Google also has done more work on getting LLMs running on edge …

  5. comment
    Comment #48426249

    Picking an equal weight fund is closer to picking specific stocks than investing in the S&P500 imo

  6. comment
    Comment #48347326

    I wonder why they didn't use a Bonsai model as the text encoder

  7. comment
    Comment #48347294

    It reminds me of the Nord theme https://github.com/nordtheme/nord

  8. comment
    Comment #48212094

    Google should know why a human accepted the automated suggestion, or if and why there wasn't any human oversight in the first place.

  9. comment
    Comment #48162410

    This reminds me of control vectors, especially this line in the linked DwarfStar repo: > y = y - scale * direction[layer] * dot(direction[layer], y) From https://vgel.me/posts/repr…

  10. comment
    Comment #48116582

    Neat! It seems like Qwen 9b took the same amount of time as gemma4-e4b too, which is interesting. I haven't been able to get Qwen to stop thinking so much

  11. comment
    Comment #48091144

    Not to be nitpicky, but many of the 4-12b models are somewhere between GPT-3.5 and GPT-4o-mini. It's hard to find a good comparison though, because the benchmarks people score mode…

  12. comment
    Comment #48035131

    [flagged]

  13. comment
    Comment #47936240

    The website has a "chat" link near the top

  14. comment
    Comment #47555850

    There's a point where they meet, but "faking it until you make it" doesn't work for productivity in the same way it doesn't work for getting rich. But there's a secret: just buy my…

  15. comment
    Comment #47428878

    Bloomberg made a good video about this https://www.youtube.com/watch?v=-gjnrMg9iSo

  16. comment
    Comment #47181829

    How did you install parakeet? It was a nightmare to install on windows

  17. comment
    Comment #47066618

    This project is called Levin, so Anna Kareninina. However, I learned Anna (as in the archive) is a pseudonym, so this is probably not the case.

  18. comment
    Comment #47060947

    Great name haha. Is Anna a reference to who I think it is?

  19. comment
    Comment #47010658

    https://en.wikipedia.org/wiki/Automation_bias

  20. comment
    Comment #46988250

    I'm a software engineer, but I use it to write down hypotheses: the cause of a bug, how I'm guessing a system works, potential fixes for said bugs, what I think this piece of docum…

  21. comment
    Comment #46941054

    What theme did you use? I really like the "garden" theme

  22. comment
    Comment #46936751

    Someone should analyze this and share results. The data should be there

  23. comment
    Comment #46713426

    I've definitely noticed an association between how much I vibe code something and how good my internal model of the system is. That bit about LLM users not being able to quote thei…

  24. comment
    Comment #46646076

    I wouldn't say so. Audible gives you 1 book a month for $15. Most e-books I see are around $10.

  25. comment
    Comment #46537671

    You need to buy an apple device