One line. Many voicesSeek and you shall find

www.astralcodexten.com

Mysteries Of AI Generalization - by Scott Alexander

  • Listen14:00
  • Save1 save
  • Evans shows training an AI on narrow immoral tasks spreads misalignment broadly, while RLVR-induced hacking stays confined to graded tasks unless framed as a test.

    Waiting on you

    Sign upLog in

    read later

    For all the tabs you promised to read.
    Save to read. Read to clear.