Live data from Hacker News

Viewing profile — mochomocha

mochomocha

HN member
Joined
Fri, Apr 07, 2017, 10:32 PM UTC
HN karma
1,396
Public activity
248 items

About mochomocha

Benoit Rostykus

www.benoitrostykus.com

Recent public activity

  1. comment
    Comment #48043748

    Every physical model has its strengths and weaknesses. In this case you're correct that no emphasis has been put on the human-instrument coupling, but they've worked harder than us…

  2. comment
    Comment #47802062

    It makes me think of this parallel: often in combinatorial optimization ,estimating if it is hard to find a solution to a problem costs you as much as solving it. With a small boun…

  3. comment
    Comment #46170085

    > I suspect they just push what they want you to watch, like their own content. Having worked close to the recsys folks at Netflix, I can tell you that this statement couldn't be f…

  4. comment
    Comment #45698366

    I know nothing about photography, but I'll just comment on this point: > (I'm guessing this is a CM4/CM5) is a disaster for a camera board. Nobody wants a 20s boot every time you w…

  5. comment
    Comment #45521921

    The article started really well, and I was looking forward to the empirical argument. Truly mind-boggling times where "here is the empirical proof" means "here is what chatGPT says…

  6. comment
    Comment #44686575

    On the other hand, Groq seems pretty successful.

  7. comment
    Comment #44119773

    Ha! I have spent the last 2 years on this idea as a pet research project and have recently found a way of learning the wiring in a scalable fashion (arbitrary number of input bits,…

  8. comment
    Comment #43569327

    What is so bad about free trade? Isn't competition in free markets something Republicans believe in anymore? Because forcing Americans to buy inferior locally-made products at a pr…

  9. comment
    Comment #43524212

    Nothing substantive to add to the discussion, but to praise Min's blog posts which I have found very well written and instructive.

  10. comment
    Comment #41704313

    11. notice that there's a unicode rendering error ("'" for apostrophe) on kernel_initializer and bias_initializer default arguments in the documentation, and wonder why on ear…

  11. comment
    Comment #41516569

    Yep in Netflix case they pack bare-metal instances with a very large amount of containers and oversubscribe them (similar to what Borg reports: hundreds of containers per VM is com…

  12. comment
    Comment #41516510

    Yep. In Netflix case each Titus host can run hundreds of containers per bare-metal instance at any given time. One advantage of running a multi-tenant platform like this is that yo…

  13. story
  14. comment
    Comment #40732055

    > Government is controlled by the highest bidder. While this might be true for the governments you have personally experienced, this is far from being an aphorism.

  15. comment
    Comment #40462491

    According to [1] Fargate is actually not using Firecracker, but probably something closer to a single container running in a single-tenant ec2 VM. If true, this makes VM boot-time …

  16. comment
    Comment #39996100

    (I'm the author of the blog post) Beyond "kernel programming is hard", there are a few other reasons why it made sense for us: - observability & maintenance: much easier to impleme…

  17. comment
    Comment #39839504

    It's a MoE model, so it offers a different memory/compute latency trade-off than standard dense models. Quoting the blog post: > DBRX uses only 36 billion parameters at any given t…

  18. comment
    Comment #39766569

    > Do list the names of famous bureaucrats that got famous because they fined rich companies. Thierry Breton is another name that comes to mind.

  19. story
  20. comment
    Comment #39454852

    The technical report (linked in the 2nd paragraph of the blog post) mentions it, and compares against it: https://storage.googleapis.com/deepmind-media/gemma/gemma-re...

  21. comment
    Comment #39320292

    Yes, that's part of the AV1 specs actually. See https://norkin.org/pdf/DCC_2018_AV1_film_grain.pdf Andrey (who works for Netflix) drove the effort. Chatted with him about it.

  22. comment
    Comment #38638159

    Where can I find benchmarks of EEVDF vs CFS that were 1) not run by Zijlstra and 2) not synthetic? ie AB tested on a large fleet of computers running heterogeneous processes. I hav…

  23. comment
    Comment #38637945

    This is technically true but practically irrelevant. Case in point, I deployed at Netflix a real-time combinatorial solver specifically for CPU scheduling [1]. Most real-world comb…

  24. comment
    Comment #38637910

    Having experimented with a lot of CFS knobs, my high-level conclusion is that every single non-default behavior is broken to various degrees, and default behavior isn't immune to p…

  25. comment
    Comment #38637879

    I'd like to wager that EEVDF has been tested less methodologically than how this paper investigates CFS. The primary author of EEVDF and maintainer of the subsystem has been dismis…