Skip to content
  • Categories
  • Recent
  • Tags
  • Popular
  • World
  • Users
  • Groups
Skins
  • Light
  • 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 (No Skin)
  • No Skin
Collapse
Code Project
  1. Home
  2. Other Discussions
  3. The Insider News
  4. Generative AI goes 'MAD' when trained on AI-created data over five times

Generative AI goes 'MAD' when trained on AI-created data over five times

Scheduled Pinned Locked Moved The Insider News
comhardwareannouncement
2 Posts 2 Posters 0 Views 1 Watching
  • 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.
  • K Offline
    K Offline
    Kent Sharkey
    wrote on last edited by
    #1

    Tom's Hardware[^]:

    Generative AI goes "MAD" after five training iterations on artificial outputs.

    "I can feel it. I can feel it. My mind is going."

    One day I'll find a decent article for a GlaDOS or Shodan quote instead of poor old HAL

    N 1 Reply Last reply
    0
    • K Kent Sharkey

      Tom's Hardware[^]:

      Generative AI goes "MAD" after five training iterations on artificial outputs.

      "I can feel it. I can feel it. My mind is going."

      One day I'll find a decent article for a GlaDOS or Shodan quote instead of poor old HAL

      N Offline
      N Offline
      Nelek
      wrote on last edited by
      #2

      Is not something similar a methode for brain washing? Why shouldn't work similar for AI? The question is... why the :elephant:? As it would not be bad enough training it with real internet data...

      M.D.V. ;) If something has a solution... Why do we have to worry about?. If it has no solution... For what reason do we have to worry about? Help me to understand what I'm saying, and I'll explain it better to you Rating helpful answers is nice, but saying thanks can be even nicer.

      1 Reply Last reply
      0
      Reply
      • Reply as topic
      Log in to reply
      • Oldest to Newest
      • Newest to Oldest
      • Most Votes


      • Login

      • Don't have an account? Register

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