It’s incredibly hard to specify things unambigiously. Even in common workday practice, communication problems cause tons of problems; you always have to make assumptions, because absolutely precise definition of everything is extremely wasteful (if it’s even possible at all). I cringe whenever someone says “But that’s obvious! You should have thought of that automatically!”. Obviously, their model of reality (wherein I am aware of that particular thingy) is flawed, since I was not.
That’s the largest problem when delegating any work, IMO—we all have different preconceptions, and you can’t expect anyone else to share all those relevant to any given task. At least anything more complicated than pure math :D
Let us know when you can encode what “physically or mentally hurt or injure any of the participants” means in an actual existing programming language of your choice. :-)
I would create the machine (genie) to respond only in ways that cannot physically or mentally hurt or injure any of the participants.
I don’t think you quite understood the article :P
It’s incredibly hard to specify things unambigiously. Even in common workday practice, communication problems cause tons of problems; you always have to make assumptions, because absolutely precise definition of everything is extremely wasteful (if it’s even possible at all). I cringe whenever someone says “But that’s obvious! You should have thought of that automatically!”. Obviously, their model of reality (wherein I am aware of that particular thingy) is flawed, since I was not.
That’s the largest problem when delegating any work, IMO—we all have different preconceptions, and you can’t expect anyone else to share all those relevant to any given task. At least anything more complicated than pure math :D
Let us know when you can encode what “physically or mentally hurt or injure any of the participants” means in an actual existing programming language of your choice. :-)