Welcome to Incremental Social! Learn more about this project here!
Check out lemmyverse to find more communities to join from here!

livescience.com

Poisoned AI went rogue during training and couldn't be taught to behave again in 'legitimately scary' study (www.livescience.com)

Poisoned AI went rogue during training and couldn't be taught to behave again in 'legitimately scary' study::AI researchers found that widely used safety training techniques failed to remove malicious behavior from large language models — and one technique even backfired, teaching the AI to recognize its triggers and better...

  • All
  • Subscribed
  • Moderated
  • Favorites
  • incremental_games
  • meta
  • All magazines