Live data from Hacker News

Viewing profile — mkagenius

mkagenius

HN member
Joined
Wed, Jan 01, 2014, 6:06 PM UTC
HN karma
3,335
Public activity
1,339 items

About mkagenius

https://instavm.io (manish [at] instavm.io)

Recent public activity

  1. comment
    Comment #49219610

    10k steps is a lot for me too.

  2. comment
    Comment #49219108

    > continued using Artifactory for their sandbox This is still fine. Infact, they had gone one step ahead by having an internal cluster of artifactory rather public managers like pi…

  3. story
  4. comment
    Comment #49178734

    > NixOS is the key to all of this, since agents can interact see the whole server config We added native support for nixos for the same reason - malleability and debugging becomes …

  5. comment
  6. story
  7. comment
    Comment #49160913

    I love how goal posts are shifting from "vibe coded apps dont really work" to "vide coded projects wont be maintained"

  8. comment
    Comment #49158942

    Couldn't find what exact tests they are running. The GitHub repo is very obscure to be read by my human brain.

  9. comment
    Comment #49158759

    If you ever need to switch sandboxes, would be happy to chat.

  10. comment
    Comment #49148086

    There is also a microvm.nix project which helped us support sandboxes with firecracker. So, whole ai workflow pipeline can now be nixos.

  11. comment
    Comment #49130761

    You can close your eyes. Tricky if it's noisy - but then that's an issue in itself.

  12. comment
    Comment #49100737

    I also just finished writing a note - https://mkagenius.substack.com/p/notes-on-mythos-breaking-ae... https://news.ycombinator.com/item?id=49099977

  13. story
  14. comment
    Comment #49092989

    If you are a pentester who uses mitmproxy you can check out security skills distilled from 4000 Hackerone public disclosures https://GitHub.com/instavm/security-skills

  15. story
  16. story
  17. comment
    Comment #49035293

    > Are you writing for an internet rando who’s got nothing better to do than to hunt for em dashes? Some people even take pride on being able to detect (often falsely) AI generated …

  18. comment
    Comment #49027143

    One was IMO gold medal winner as well.

  19. comment
    Comment #49019249

    Specific quirk of llms, also pretty much solved by existing thinking models. I think you guys are misunderstanding me, you can still talk to a llm to learn everything about physics…

  20. comment
    Comment #49018611

    they are wrong on the specific nuance of my codebase too, i am talking about learning something - i can still learn everything about software engineering talking to a bot.

  21. comment
    Comment #49017712

    They are solving jacobian conjectures, I don't think they will hallucinate till masters level of any subject. Edit: do give counter examples if you have any in maths, physics, chem…

  22. comment
    Comment #49017604

    > I can't use it for theoretical physics because I can't evaluate the responses. I think pretty much the opposite. I can ask it to explain to me in ways I understand it. Even drill…

  23. comment
    Comment #48999046

    It's also unclear what kind of sandboxing they are referring to. Is it the codex one - coz that one has built-in ways to circumvent guardrails, for example by "just asking user" an…

  24. comment
    Comment #48975918

    You might want recheck your theory - https://news.ycombinator.com/item?id=48970377

  25. comment
    Comment #48972416

    What I meant to say there is, all the bloats are going away as we speak, is the bun rewrite a bloat? A slop? why would you call it one if it's not. What if we used AI in a way that…