Live data from Hacker News

Viewing profile — ashvardanian

ashvardanian

HN member
Joined
Fri, Nov 26, 2021, 7:28 PM UTC
HN karma
4,504
Public activity
829 items

About ashvardanian

Bootstrapping since 2015. Investing at . Hosting ML/Systems hackathons around the globe. Living between London, San Francisco, and Yerevan. Converting outrageous amounts of coffee into modest amounts of Assembly for Intel, Arm, and Nvidia chips. Maintaining FOSS libs deployed on ≫ 100M devices.

Recent public activity

  1. story
  2. story
    Show HN: ForkUnion v3 – Faster OpenMP-style thread-pool for C, C++, Rust, & Zig

    Hi community! Wanted to share a project of mine that is now enabling parallelism across many of my open-source projects: ForkUnion. The absolute majority of "thread pool" projects …

  3. story
  4. comment
    Comment #48740737

    Got really excited for this model and asked my Opus planners in 3 pretty different projects to use Sonnets instead of Opus subagents to help me experiment on HPC kernels faster. No…

  5. story
  6. story
  7. comment
    Comment #48295153

    I really like the speed at which Cloudflare is executing toward becoming a critical infrastructure player with all of those new product offerings. That said, not everything needs t…

  8. story
  9. story
  10. story
  11. story
  12. story
  13. comment
    Comment #47469400

    I'm not aware of that, but it would likely be a great application area for SME!

  14. comment
    Comment #47464359

    The README was written by a human. I’ve used models extensively to refine the content, but never accepted more than a couple of lines of edits at a time.

  15. story
  16. story
  17. comment
    Comment #47388532

    I don't have the inside scoop on Intel's current mess, but they definitely have a habit of killing off their coolest projects.

  18. comment
    Comment #47337005

    Would it be accurate to say that Meta currently produces more RISC-V chips than other vendors? The specs for those chips look extremely interesting and seem much more programmable …

  19. story
  20. comment
    Comment #47024217

    https://www.bloomberg.com/news/articles/2026-02-10/nebius-ag... https://www.tavily.com/blog/tavily-is-joining-nebius

  21. story
  22. comment
    Comment #47020007

    8K QPS is probably quite trivial on their setup and a 10M dataset. I rarely use comparably small instances & datasets in my benchmarks, but on 100M-1B datasets on a larger dual-soc…

  23. story
  24. story
  25. story