Slashdot Mirror
Team Aims To Create Pure Evil AI
puroresu writes "Scientific American reports on the efforts of Selmer Bringsjord and his team at the Rensselaer Polytechnic Institute, who have been attempting to develop an AI possessed of an interesting character trait: pure evil. From the article, 'He and his research team began developing their computer representation of evil by posing a series of questions beginning with the basics: name, age, sex, etc., and progressing to inquiries about this fictional person's beliefs and motivations. This exercise resulted in "E," a computer character first created in 2005 to meet the criteria of Bringsjord's working definition of evil. Whereas the original E was simply a program designed to respond to questions in a manner consistent with Bringsjord's definition, the researchers have since given E a physical identity: It's a relatively young, white man with short black hair and dark stubble on his face.'"
I suspect that they(ironically detracting from their goal) went down the path of maximising for "threatening" or "untrustworthy", rather than evil(which is much harder to depict, without falling into specific cliche-riddled stuff).
A fair few studies suggest that a face that looks about like that one, with more or less unpleasantly masculine features, rates low on perceived trustworthiness and high on perceived threat. Of course, the evil that you don't recognize is way more dangerous than the obvious one, so choosing that is kind of silly; but I'm not too surprised that they did.
Not necessarily: religious nutjobs' reasons are bullshit; but they are often quite coherent bullshit. Moreover, religious nutjobs generally subscribe to some flavor of a divine command theory of ethics and believe that they are carrying out divine instructions, which logically implies that they do not believe that they are carrying out a morally wrong action.(Arguably, divine command theories of ethics are incoherent, Plato having more or less shoved a stake in their heart ages ago; but they are quite common and quite commonly believed, even on inspection, to be coherent).
If anything, the most dangerous nutjobs are characterized by their extreme degree of value-rational conduct. In the case of pretty much any religious nutjob of note, you'll find, either around them or in the society that spawned them, numerous people who embrace the same epistemological and metaphysical convictions who, nevertheless, are only modestly dangerous, at most, because they do not follow their convictions through to their rational conclusion.
From the article:
This sounds to me more like cruelty, which is certainly a kind of evil, but by no means the only one. It's also more than a little cartoonish: this is someone who appears to do harm simply for the sake of causing harm (i.e. for the lulz?), rather than the more carefully rationalized evil seen as realistic today. How useful will that really turn out to be?
Isn't it wonderful to be in the world today, where everyone can be racist against whites without fear of reprisal?
So to summarize...nobody is the villain in their own story.
"Never let your sense of morals prevent you from doing what is right" - Salvor Hardin
What if your dog tells you to do something....like kill people?
Are you evil or is the dog?
The dog is evil, and you are silly for blindly obeying the commands of a dog.
The real question is, what if your God tells you to do something.. like kill people?
Are you evil, or is your God?
I don't care if it's 90,000 hectares. That lake was not my doing.
After reading the article I think the kery thing this research has proven is that being a great computer scientist does not necessarily guarantee you'll be an even passable philosopher or psychologist.
They needed a character that wouldn't be perceived as racist or genderist, so only a white male would be the Politically Correct safe choice.
"This post is an artistic work of fiction and falsehood. Only a fool would take anything posted here as fact."
I view "Good" and "Evil" to a large extent as imaginary terms that we apply to people who agree or disagree with us. True you could manipulate people for your own goals without regard for their welfare or the consequences of your actions and that would be fairly evil, but usually you view your goals as "good" and furthering them as good for everyone, even if they don't realize it at the time.
I'm trying to teach myself to set people on fire with my mind... Is it hot in here?
Bravo. If I had mod points, they'd be yours.
Truth be told, I dislike the way his plan is turning out. I'm really not sure what I should feel, as the system is so complicated that I doubt ANYONE truly knows what is best. All I do know to believe is that there are people who go broke through complicated (and often unnecessary) medical procedures. Worse, because they can't afford them, some people go without them completely and end up with worse conditions that hospitals have to deal with in the end. This is unacceptable as a citizen and as a human being.
I recall reading a Republican Representative's quote in Time magazine a while back about how if they can beat Obama's healthcare plan, they'll beat HIM. That, to me, is pure evil. They oppose a plan not because it's in the best interest of the people (or so they believe, in any case) but because they want political power.
Minority white farmers in Zimbabwe care as they're driven off their land and out of the country by the powerful ultra racist black majority...
When are the people who constantly condemn the evil racist white man going to start condemning the racist apartheid black mans state of Zimbabwe?
That would be never.