Google DeepMind releases its plan to keep AGI from running wild

Jump to latest Follow Reply
Status
You're currently viewing only Handmaden of Sappho's posts. Click here to go back to viewing the entire thread.
Sort by date Sort by votes
H

Handmaden of Sappho

Seniorius Lurkius
22
Subscriptor
  • #67
    To avoid that, DeepMind suggests developers use techniques like amplified oversight, in which two copies of an AI check each other's output, to create robust systems that aren't likely to go rogue. If that fails, DeepMind suggests intensive stress testing and monitoring to watch for any hint that an AI might be turning against us.
    Click to expand...
    I believe upping it to three systems and giving them some religiously-coded names might be the winning strategy here, actually.

    a-magi-system-of-mine-v0-y32x9gplfk0b1.png
     
    Upvote
    10 (10 / 0)
    You must log in or register to reply here.
    Status
    You're currently viewing only Handmaden of Sappho's posts. Click here to go back to viewing the entire thread.
    Jump to latest Follow Reply
    Jump to latest Follow Reply