Live data from Hacker News

Viewing profile — marmaduke

marmaduke

HN member
Joined
Tue, Apr 10, 2012, 7:28 PM UTC
HN karma
2,806
Public activity
1,519 items

About marmaduke

[ my public key: https://keybase.io/wdmn; my proof: https://keybase.io/wdmn/sigs/KaH_BqIpR_cc-JNsLgWnzWCnKy_ZnbQfoKTC0ms3-1o ]

Recent public activity

  1. comment
    Comment #42723661

    similar to RWKV7’s new (sub quadratic) attention mechanism which models key values as v≈kS’ and does an in-context descent on ||v - kS’||^2/2 (where the state matrix S is one atten…

  2. comment
    Comment #42672039

    ha, yeah, thanks.

  3. comment
    Comment #42669134

    no, wrote it by hand for use with my own Heun implementation, since it’s for use within stochastic delayed systems. jax is fun but as effective as i’d like for CPU

  4. comment
    Comment #42667924

    looks like a nice overview. i’ve implemented neural ODEs in Jax for low dimensional problems and it works well, but I keep looking for a good, fast, CPU-first implementation that i…

  5. comment
    Comment #42614422

    i like how the contraction it’s and abbreviation T’is are anagrams

  6. comment
    Comment #42580346

    I didn’t look it up, but at first glance, it reminded me of discussions like this one https://youtu.be/qnT48wO0UL0

  7. comment
    Comment #42565805

    that’s not what the story says. in any case, the point is to explain, in terms of dualistic if-then logic, that the if (you practice now) and then (you will wake up) are a single n…

  8. comment
    Comment #42555214

    do you have a link for your game? how was the release process?

  9. comment
    Comment #42534004

    how far from your previous experience is the game work?

  10. comment
    Comment #42507852

    i wonder if there are any semi automated approaches to finding outliers or “things worth investigating” in these traces, or is it just eyeballs all the way down?

  11. comment
    Comment #42507825

    https://www.biorxiv.org/content/10.1101/2024.10.25.620245v1.... covers some of the recent perspectives on this modeling approach if you’re interested.

  12. comment
    Comment #42504596

    having worked on whole brain modeling the last 15 years and european infra for supporting this kinda research, this is a terrible buzzword salad. the pdf is on par with a typical m…

  13. comment
    Comment #42504574

    HH is kinda the opposite of LIF on the abstraction spectrum.

  14. comment
    Comment #42287364

    The pigeon experiment is a great one to learn from not just about programming or software, but about life in general. Where are you getting your next dopamine hit? Is it random? Ma…

  15. comment
    Comment #42282006

    > CPUs have the memory capacity advantage perhaps also more precisely they also have quite an advantage on anything that needs and plays nicely with caches? when I sliced my proble…

  16. comment
    Comment #42281655

    My approach to this is to write a bunch of tiny “kernels” which are obvious to SIMD and then inline them all, and it does a pretty good job on x86 and arm https://github.com/maedoc…

  17. comment
    Comment #42268280

    > People won't even pay for most of these pocket distractions If someone is paying, the transaction, by construction reinforces the psychological boundaries that obliteration elimi…

  18. comment
    Comment #42229795

    I think “a cloud never dies” is more apt for this sentiment

  19. comment
    Comment #42144836

    How would you want to host or update the markdown file? Sending an email for instance? Or run your own host?

  20. comment
    Comment #42096191

    > Unlike most prior efforts, we release not only model weights and inference code, but also the reproducible training data, complete data processing pipeline, rigorous experimental…

  21. comment
    Comment #42041641

    Just brainstorming here, but as a parent and someone who subscribed to a weekly CSA, it’d be a big boost to be able to take a picture of what I’ve got and get some ideas about reci…

  22. comment
    Comment #42039460

    At the risk of taking some heat, I’d wager a preprint is recognized rightly by the Chinese as a flag planting, we’re first formality, where in the faults may even serve to validate…

  23. comment
    Comment #41913310

    I tend to think of science as a distributed consensus process, and that peer review is analogous to a proof of work, and publishers are gatekeeping the distribution of proof of wor…

  24. comment
    Comment #41907005

    Was your path towards the decision point a sudden one or a slow burn?

  25. comment
    Comment #41888575

    Good question, I only looked briefly at unscented, I just thought ensemble was easy to understand.