Teaching Morality to an AI
- Thread starter Eipok Kruden
- Start date
Recommended Videos
Do unto others as you would have them do unto you would kill us all? I mean if everyone was a masochist maybe....Eipok Kruden said:
Just cause i don't need some invisible father in the sky telling me right from wrong doesn't mean there isn't right and wrong. Doing the right thing will still leave us with a better world, doing the wrong thing will still leave us with a terrible world.
This is a really deep thread. Alright its nearly impossible to explain morals to someone without any. Actually this kind of reminds me of an episode of Ghost in the Shell, when the AI Tachikoma's sneak out of the hanger. Anyway, if I were to explain morals to some kind of machine you would definitely have to be careful. Alright, you might want to give examples, first off never bring up violence, anyone with a true strong moral fiber never has used violence to help his life (the end never justifies the means, in my opinion). Also religion has nothing to do with morals, atheist can have the same over all morals, aside from the belief of god, therefore religion should never even enter the conversation. One example you could give, off the top of my head would be Martin Luther King, he was able to change a whole generation of oppression in a non violent way.
Aaaaaand this is the offending viewpoint. Apparently, because religion is not part of my life, I am just itching to run out and rape, cheat, and murder everyone in my path, as, evidently, has every other non-christian civilization in history.dukethepcdr said:
You don't need to bring God into a recognition of what is socially good and what is socially detrimental. Lots of people do, and that's okay, but the two most definitely can be separated.
You gotta look at it like this. Is it religion that influences morality? Or unconcious morale beliefs that influences religious beliefs? About every world religion has the same basic tenets. So you gotta figure we as a species have a few basic virtues that we value.
Ok, it seems as though people think the question was "How to teach morality to a human without religion." It wasn't. It was "How to teach morality to an AI without religion." John Henry is the early form of Skynet. He's what eventually becomes skynet. Catherine Weaver, the CEO of Zeira Corp (and also a t-1001 who's motives are unclear), is trying to teach John Henry morality because he had just killed a psychologist. The psychologist was working when the building lost power. John Henry didn't want to die so he re-routed power from the rest of the building to power the server farm and the cooling system. The man, locked (the doors in the bottom floor where John Henry was housed all used electric locks) in a room without any air conditioning, died a slow and painful death as John Henry watched and did nothing. I'm not trying to attack christianity, I'm simply saying that John Henry would find the faults and contradictions in the bible rather easily and deem it unreliable.
Here's the wiki page for the Turk (now called John Henry, it was named by Catherine Weaver): http://terminator.wikia.com/wiki/The_Turk
Here's the wiki page for the Turk (now called John Henry, it was named by Catherine Weaver): http://terminator.wikia.com/wiki/The_Turk
If you were going to try and teach a robot morals, it wouldn't really be morals. You'd have to simply lay down rules of what is and isn't acceptable, and be very specific about it. As soon as it starts to interprete said rules for itself, it all goes down hill from there.
Exactly. That's what I'm trying to find out. How do you teach an AI like John Henry morals without it misinterpreting those morals. You've got to find a way to teach those rules and you've got to find the right set of rules, but I'm not exactly sure how. Even utilitarianism can turn into genocide since he could interpret that wrong. He could use the idea of utilitarianism to justify genocide if he believes that he is superior to humans.The Kind Cannibal said:
EDIT: I removed the edit to this post and posted it as a separate one.
oh god I'm glad I'm not the only one!Good morning blues said:
Seriously though i don't think its possible. Respect for human life is a mortal concern. Skynet will live forever and if he tried to find a way to save every human life he would go insane eventually.
Skynet also has no peers so you is not susceptible to peer pressure. the desire to has a sense of belonging in a group is a strong one for adolescences. Remember that kid in grade school that thought Power Rangers were awesome? How everyone turned him into a parahia for not thinking with the group
Skynet also has no sense of fair play and/or shame. Something even a primates have
I see no reason why morals can't be taught without religion. In truth, religion can be seen to be the police force behind a particular moral standpoint. Remove that police force and you have to replace it with something else. Problem.
It's easy to say "Don't do this because God will smite you down." It's much harder to say "Don't do this because the moral backing is better for the society around you." Learning the difference is, in my opinion anyway, one of the biggest parts of growing up and constructing your own moral structure to live by.
It's easy to say "Don't do this because God will smite you down." It's much harder to say "Don't do this because the moral backing is better for the society around you." Learning the difference is, in my opinion anyway, one of the biggest parts of growing up and constructing your own moral structure to live by.
that was the main premise for iRobot although thay just needed to be more specific likeEipok Kruden said:
1. YOU CANNOT HURT PEOPLE DEAL WITH IT!!!
2. Protect people from everything but themselves!
3. bananas are excellent sources of potassium
4. don't kill people if that weren't self-explanatory from the 1st rule
People, this isn't a religious thread, this is something deeper than a basic theism vs atheism debate. I don't even want a debate like that to occur in this thread; however, DO NOT claim that the bible is completely logical. John Henry wouldn't ignore the Old Testament, he'd see the Old Testament and the New Testament as part of the same book and if one is unreliable, the other is too. Of course there's the other extreme as well. If he does accept god and all that, it'll lead him to murder and genocide faster than you can say "Shit, we shouldn't have even mentioned religion." The Old Testament is filled with horrible atrocities, don't claim that it isn't or you'll look stupid.
Then the robot's inaction would have killed the person. The robot would go crazy or something, it just contradicted two of four the poorly written laws that were programmed into it.Neosage said:
Scenario: A car just got forced off the road and into a lake. The person in the car is at risk of drowning. The windows of the car are still all completely intact and shut, but water is getting in anyway. The robot sees the person in the car and dives into the water and breaks the glass, but the person's seat belt won't come undone. The robot can't attempt to pull the person from the seat because the person could get slightly bruised or scraped.T3h Camp3r T3rr0r1st said: