Making a Superintelligence: AI Safety and the Control Problem - Couverture souple

Verma, Utkarsh

 
9798328895156: Making a Superintelligence: AI Safety and the Control Problem

Synopsis

As we attempt to conquer intelligence using machines, it is important that we proceed with caution to ensure that our innovations are beneficial to us. Hence, as humanity attempts to make a superintelligence, it it of upmost importance that we ensure that it is safe. This books discusses the challenges that must be overcome and the questions that must be answered in order to do so.

Les informations fournies dans la section « Synopsis » peuvent faire référence à une autre édition de ce titre.