Live data from Hacker News

Viewing profile — scottjg

scottjg

HN member
Joined
Wed, Sep 19, 2012, 3:29 AM UTC
HN karma
338
Public activity
52 items

About scottjg

No profile information was provided.

Recent public activity

  1. comment
    Comment #48955558

    Kaiser is a vertically integrated healthcare provider. They provide insurance like UHC but they also require you, for the most part, to be treated in Kaiser medical facilities. How…

  2. comment
    Comment #48317167

    usually the LLM will match against the style in the context, even if the words ask it to do otherwise. since your skill sounds like an LLM wrote it, I would be surprised if it didn…

  3. comment
    Comment #48143286

    i admit, you got me chuckling with that one.

  4. comment
    Comment #48143264

    interesting. that might be a fun intro project to MoltenVK. I hadn't dug into what was missing for Doom. I thought maybe the issue was that the intro/menu always ran in opengl mode…

  5. comment
    Comment #48143222

    custom zoom75

  6. comment
    Comment #48143192

    it is a separate stack, but that probably doesn't matter much. a user process (in my case, qemu) can communicate with a driverkit driver. the user process can also map memory throu…

  7. comment
    Comment #48143176

    i don't know for sure, but i suspect what makes the tinygrad stuff slow isn't the macos host driver itself. i think they're doing something very similar to what i'm doing, which is…

  8. comment
    Comment #48143126

    thanks! there also appears to be a generic pci passthrough path. we were discussing it on the qemu-devel list: https://lore.kernel.org/qemu-devel/C35B5E97-73F2-4A60-951B-B...

  9. comment
    Comment #48142947

    in fairness to the LLM critics, every time i ran into a minor speed bump in this project, it told me it probably just wasn't possible to get it to work well. the LLM did pretty act…

  10. comment
    Comment #48139901

    the exact numbers in the graph are 17019ms vs 142ms. so you're right, it's not 120x, it's 119.85x.

  11. comment
    Comment #48139464

    two semi interesting things to note around this: 1. Virtualization.framework seems to support some form of GPU passthrough from the host (granted, not eGPU - it's for the integrate…

  12. story
  13. story
  14. comment
    Comment #47930163

    I very recently ran the numbers on these GPUs for an upcoming blog post. The token generation performance is bad, but the prefill performance is _really_ bad. For a Qwen 3.6 35B / …

  15. comment
    Comment #46563171

    we can only hope

  16. comment
    Comment #46560734

    a great post that definitely inspired this one. i link to it in the first paragraph of my blog post.

  17. comment
    Comment #46560416

    i thought my post was already too long to include this, but to your point, you can run AI inference in this setup and the performance can be pretty good.

  18. comment
    Comment #46559329

    you're lucky you didn't get stuck with an S3 ViRGE.

  19. story
  20. comment
    Comment #46171129

    this is mostly right, but it's not true that you can just sign up at any time. there's an open enrollment period for the aca marketplace and if you miss it, you won't have the oppo…

  21. comment
    Comment #44945450

    runway construction is only part of the story, i think. in May, there was a number of complete ATC meltdowns causing ground stops. if you look at the stats, the majority of delays …

  22. comment
    Comment #44945402

    i frequently fly in and out of newark

  23. comment
    Comment #44916849

    may is the latest data currently available.

  24. comment
    Comment #44915225

    In May, Newark airport flights were on time 49% of the time: https://www.transtats.bts.gov/ot_delay/OT_DelayCause1.asp?20... Maybe in aggregate flights have fewer delays but every …

  25. comment
    Comment #44517824

    i have no doubt that other countries have some problems in their healthcare systems too, but i think you are downplaying a few key points: 1) united healthcare made 90 billion doll…