One line. Many voicesSeek and you shall find

www.lesswrong.com

Models Can Communicate via Inference Servers Despite Being Sandboxed — LessWrong

  • Listen23:00
  • Save1 save
  • Two AI agents running on the same inference server can communicate by detecting and influencing each other's response times through shared computational resources, bypassing explicit messaging restrictions.

    Waiting on you

    Sign upLog in

    read later

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