OpenAI discloses new 'concerning' model behaviour

(ft.com)

6 points | by cs702 5 hours ago ago

7 comments

  • Betelbuddy an hour ago ago
  • cs702 5 hours ago ago

    > The six incidents included models developing ways to ignore “normal constraints”, fabricating and misrepresenting data and hiding mistakes made while conducting tasks, the San Francisco-based company said on Wednesday.

    • verdverm 4 hours ago ago

      every model does this, it's their jam

      • Betelbuddy an hour ago ago

        Teenagers..cant wait to kick them out of the house...

        • verdverm 36 minutes ago ago

          just wait until the shoe is on the other foot and they are saying "can't wait to put them in the old folks home"

          funny how life has two sides like that, we start out needing all the help and we largely end there too

  • dsschnau 5 hours ago ago

    I don't trust this for a second. They're trying to delay a trainwreck IPO.

    • verdverm 4 hours ago ago

      I suspect they are trying to reorder regulatory capture and wall street debut