Sublime

Artificial general intelligence would be a major turning point in the relationship between humans and machines—what many predict would be the most significant single event in the history of the human race. It’s a milestone that I believe we should not cross unless we have first definitively solved all problems of control and safety. But given the r

To be clear, none of the scenarios described above—the immortal digital minds or omnipotent superintelligences—are possible based on today’s technologies; there remain no known algorithms for AGI or a clear engineering route to get there. The singularity is not something that can occur spontaneously, with autonomous vehicles running on deep learnin

What’s difficult is to state our aesthetic values clearly enough to enable the program itself to make the evaluation at each generation.

The AI control problem is defined as the problem concerned with how to build superintelligence that will aid its creators, and avoid the chances of it deliberately or inadvertently causing harm.