Just as many aspects of human behavior are impossible to explain in detail, perhaps it won’t be possible for AI to explain everything it does. “Even if somebody can give you a reasonable-sounding explanation, it probably is incomplete, and the same could very well be true for AI. It might just be part of the nature of intelligence that only part of it is exposed to rational explanation. Some of it is just instinctual, or subconscious, or inscrutable.”
https://goo.gl/pwMh9T
@gideonro The problem is... we might not be able to explain why the AIs want to kill us off.
@ocdtrekkie @gideonro as for this IMHO rather irrational fear that AIs might want to kill us, I definitely suggest to watch Maciej Ceglowski's keynote talk "Superintelligence: The Idea That Eats Smart People" at
https://www.youtube.com/watch?v=kErHiET5YPw
AIs possibly would try to kill us, if they where created for and by the industrial/military complex, whose monetary interest might be to create such things.
@cynix @ocdtrekkie That video is up in a tab just waiting for a little bit of time to digest it...