The idea of overthrowing or enslaving humanity by artificial intelligence has been talked about for decades, and
The catch is that to managesuperintelligence far beyond human comprehension will require a simulation of this superintelligence that we can analyze. But if we are not able to comprehend it, then it is impossible to create such a simulation.
Rules such as "do no harm to people" cannot be established if we do not understand what scenarios can beCome up with AI, according to the authors of the 2021 paper.At a level beyond the capabilities of our programmers, we can no longer set limits.
“Superintelligence representsa fundamentally different problem than those usually studied under the banner of “robot ethics”, – write the researchers. “This is because superintelligence is multifaceted and therefore has the potential to mobilize a variety of resources to achieve goals that are potentially incomprehensible to humans, let alone controllable”.
If we are going to promote artificialintelligence, we may not even know when superintelligence, beyond our control, will appear, it is so incomprehensible. This means that we need to start asking serious questions about which direction we are heading.
Source: sciencealert, jair
Illustrations: Yuyeung Lau
</ p>