Live data from Hacker News

Viewing profile — shay_ker

shay_ker

HN member
Joined
Fri, Sep 21, 2018, 5:53 AM UTC
HN karma
692
Public activity
286 items

About shay_ker

you can dm me on twitter, @__smiz

Recent public activity

  1. comment
    Comment #49216038

    how do any of these routing approaches handle kv cache misses? Devin Fusion is the only one that explicitly addresses this, though it does so by switching models during compaction …

  2. comment
    Comment #49214427

    i'm surprised there isn't more commentary on the vulnerabilities themselves (mostly in apps developed on the jvm, e.g. artifactory)

  3. story
  4. comment
    Comment #49159408

    Separately, JetBrains's revenue grew 25%: https://www.jetbrains.com/lp/annualreport-2026/ But back to OP, for this prompt: > Set up a nightly cron job that executes the prompt: fet…

  5. story
  6. story
  7. story
  8. story
  9. comment
    Comment #48984835

    How do we know if these models weren’t trained on Turso’s rewrite of SQLite in Rust? It seems both likely that they were and impossible to remove that code from pretraining. Doesn’…

  10. comment
    Comment #48922468

    How much do the labs post-train on the harness inputs & outputs? That's a critical piece to understand if a "generic" harness is at all possible

  11. comment
    Comment #48886703

    There's no free lunch. Housing costs are effectively carried by immigrants and transplants: https://www.aei.org/wp-content/uploads/2023/09/Setting-the-r... In general, the Vienna m…

  12. story
  13. comment
    Comment #48837694

    Didn't we all know from the start that all of SWE-Bench was flawed? Even the authors concede the limitations and have long since moved on.

  14. comment
    Comment #48836524

    Great work! My question is about what you mentioned at the end - how well do world models operate when out of distribution? In some sense we hope these models learn something "deep…

  15. comment
    Comment #48823631

    I saw the integration with Hono - hadn't heard of it before, do many people use it?

  16. comment
    Comment #48823546

    I'm curious if this approach can be generalized beyond "doom loops". For instance, another way of thinking about a "doom loop" is wasted tokens, which happens all the time with lar…

  17. comment
    Comment #48809912

    cost per benchmark task is definitely interesting! i've always wanted cost per prompt, but even that has too much variation.

  18. comment
    Comment #48490436

    random thought, but i wonder if html-in-canvas can really improve development for visualization tools specifically

  19. comment
    Comment #48460695

    I have a naive question: why did this take 15 years? I understand that good APIs need time and thoughtful design, but I struggle to understand why we couldn’t get to the same (or b…

  20. comment
    Comment #48390471

    I do wonder - why not add this to jsx?

  21. comment
    Comment #48388125

    Seems like Angular has gotten better since v2 (my last experience). Has anyone done a modern Angular vs. React comparison that's not an AI slop article? I'm also curious if it's "s…

  22. comment
    Comment #48366005

    It's fascinating that cloud providers like AWS/GCP/Azure are now immovable "enterprise" technologies, in the way that IBM, Oracle, SAP, etc. were 15 years ago (and still are!). Fon…

  23. comment
    Comment #48332627

    hmm it does seem like a good point that browsers should be able to do this natively. the DOM already holds the content, and browsers manage what's rendered in the viewport.

  24. comment
    Comment #48281361

    hot take: token spend can be used a honey pot, especially when compared to what you deliver. spend accordingly!

  25. comment
    Comment #48238235

    In the three options OP presents, I wonder if there's a fourth: BYO model Customers give vendors metered access to their model. They can budget tokens per vendor. Vendors selling "…