Live data from Hacker News

Viewing profile — haykmartiros

haykmartiros

HN member
Joined
Tue, Apr 17, 2018, 8:41 PM UTC
HN karma
473
Public activity
54 items

About haykmartiros

https://haykmartiros.com

Skydio, SymForce, Riffusion

Recent public activity

  1. comment
    Comment #43547925

    Riffusion (gen music) | san francisco | in person | 200-300 + equity training frontier music generation models and building the most powerful and fun music creation product in the …

  2. comment
    Comment #42920250

    Riffusion | Generative Music | San Francisco (in person) | $180-300k + equity Riffusion is a 10 person team making a music platform where you can create any music you imagine. We a…

  3. comment
    Comment #42018303

    Riffusion (AI Music) | San Francisco (in person) | $200-300k+ equity We're building the best music creation and listening experiences ever made, by making music interactive in new …

  4. comment
    Comment #41047853

    Longer story: The web demo is a way to earn your curiosity. The Riffusion crew is released our free iOS app today, and that's the real juice. We’re thinking constantly about how to…

  5. comment
    Comment #41047822

    One of the authors here. Short story is, check out our web demo (on desktop Chrome) for real-time music generation and editing! Music is made on the fly by our diffusion models as …

  6. story
  7. comment
    Comment #40846694

    Riffusion | Generative Music | San Francisco, CA Looking for world class ML research engineers and scientists to join our core team building the future of music. If you love creati…

  8. comment
    Comment #39219017

    Skydio - Autonomy Infrastructure | Bay Area - San Mateo | Python & C++ Skydio is the leading US drone company and the world leader in aerial autonomy. Our mission is to make the wo…

  9. comment
  10. comment
    Comment #38491211

    Skydio - Autonomy Infrastructure | Bay Area - San Mateo | Python & C++ Skydio is the leading US drone company and the world leader in aerial autonomy. Our mission is to make the wo…

  11. story
    Show HN: Vocal timing conditioned audio diffusion in real-time

    We've been cooking up a new experiment where you can record yourself singing or talking and the app will generate vocals to match your words and timings. It's backed by an end-to-e…

  12. comment
    Comment #37922220

    as of a few minutes ago, you can mark individual riffs as public or unlisted, in addition to the global setting!

  13. comment
    Comment #37921560

    Remix is using latent space interpolation under the hood to generate three variations of a given riff with (light, medium and heavy) modifications

  14. story
    Show HN: Riffusion with Lyrics

    Almost a year ago someone stumbled upon our hobby project and posted it to HN (edit: https://news.ycombinator.com/item?id=33999162 ). It was magical to see so many of you enjoy som…

  15. comment
    Comment #37792883

    This is flat out not true. Generative AI is meant to approximate the distribution. It’s biased from the data, yes, but if it was just the median it would only spit out one face, on…

  16. comment
    Comment #35242394

    Ground truth

  17. comment
    Comment #34984678

    Skydio | AI Engineer | SF preferred, remote possible. Skydio is the leading U.S. drone maker and world leader in autonomous flight. We create the world’s most intelligent flying ma…

  18. comment
    Comment #34151174

    We were blown away by the community interest in our Riffusion experiment (see https://www.riffusion.com/about ). We're now catching up and did a full rewrite to go from a hack to a…

  19. story
  20. comment
    Comment #34040347

    Absolutely legendary game.

  21. comment
    Comment #34021542

    That makes a lot of sense, I would be keen to see attempts at that.

  22. comment
    Comment #34006526

    Love this idea. If I had more time I wanted to make a spaceship game where you are flying around the latent space, and model interrogation is used to provide labels to landmarks as…

  23. comment
    Comment #34005417

    To be honest, we're not sure how much value image pre training brings. We have not tried to train from scratch, but it would be interesting. One thing that's very important though …

  24. comment
    Comment #34003015

    LOL. Yes we had to upgrade our Vercel tier: https://twitter.com/sethforsgren/status/1603425188401467392

  25. comment
    Comment #34002891

    We took a look at encoding phase, but it is very chaotic and looks like Gaussian noise. The lack of spatial patterns is very hard for the model to generate. I think there are tons …