Skip to content
  • Categories
  • Recent
  • Tags
  • Popular
  • World
  • Users
  • Groups
Skins
  • Light
  • Brite
  • Cerulean
  • Cosmo
  • Flatly
  • Journal
  • Litera
  • Lumen
  • Lux
  • Materia
  • Minty
  • Morph
  • Pulse
  • Sandstone
  • Simplex
  • Sketchy
  • Spacelab
  • United
  • Yeti
  • Zephyr
  • Dark
  • Cyborg
  • Darkly
  • Quartz
  • Slate
  • Solar
  • Superhero
  • Vapor

  • Default (Cyborg)
  • No Skin
Collapse
Brand Logo

CIRCLE WITH A DOT

  1. Home
  2. Uncategorized
  3. There we go - my opinions on "vibe coding" after having actually created a full working app with it - as a senior Software Engineer and Cybersecurity expert.

There we go - my opinions on "vibe coding" after having actually created a full working app with it - as a senior Software Engineer and Cybersecurity expert.

Scheduled Pinned Locked Moved Uncategorized
vibecodingcodingsoftwarecybersecurity
2 Posts 1 Posters 0 Views
  • Oldest to Newest
  • Newest to Oldest
  • Most Votes
Reply
  • Reply as topic
Log in to reply
This topic has been deleted. Only users with topic management privileges can see it.
  • troed@swecyb.comT This user is from outside of this forum
    troed@swecyb.comT This user is from outside of this forum
    troed@swecyb.com
    wrote last edited by
    #1

    There we go - my opinions on "vibe coding" after having actually created a full working app with it - as a senior Software Engineer and Cybersecurity expert.

    Link Preview Image
    Vibe coding results

    Vibe coding is the name given to just prompting an LLM to implement according to your directions. In this post I detail what my experience is after having done just that, viewed from the point of a senior Software Engineer and Cybersecurity expert.

    favicon

    Things I couldn't find elsewhere (blog.troed.se)

    #VibeCoding #Coding #Software #CyberSecurity

    1 Reply Last reply
    0
    • troed@swecyb.comT This user is from outside of this forum
      troed@swecyb.comT This user is from outside of this forum
      troed@swecyb.com
      wrote last edited by
      #2

      @primeapple With bad code I mean things like code duplication instead of refactoring into common methods, dead code and common security pitfalls. I agree tools could catch some of it, but mostly it comes from the models producing "junior level output" which isn't very surprising due to how LLMs work.

      I'm sure Amazon uses the very best of models and tools - yet they also need senior developers to act as code reviewers to stop bad quality from negatively affecting their uptimes.

      I don't think the current LLM paradigm can solve this. We'll need AIs that retrain during usage for that (like our human brains do 😉

      1 Reply Last reply
      1
      0
      • R relay@relay.infosec.exchange shared this topic
      Reply
      • Reply as topic
      Log in to reply
      • Oldest to Newest
      • Newest to Oldest
      • Most Votes


      • Login

      • Login or register to search.
      • First post
        Last post
      0
      • Categories
      • Recent
      • Tags
      • Popular
      • World
      • Users
      • Groups