A Cognitive Science researcher at Rensselaer is plumbing the roots of human evil by developing a computer program to simulate it. Selmer Bringsjord has created a checklist to determine whether someone is “demonic,” and is working with a team of grad students to create a computerized representation of a truly evil person.

To be truly evil, someone must have sought to do harm by planning to commit some morally wrong action with no prompting from others (whether this person successfully executes his or her plan is beside the point). The evil person must have tried to carry out this plan with the hope of “causing considerable harm to others,” Bringsjord says. Finally, “and most importantly,” he adds, if this evil person were willing to analyze his or her reasons for wanting to commit this morally wrong action, these reasons would either prove to be incoherent, or they would reveal that the evil person knew he or she was doing something wrong and regarded the harm caused as a good thing.

The result is “E,” which resides in his (they’ve developed a physical persona–a young white male) own virtual world and can be queried about his motives via avatar. Right now the interface is fairly basic, but they’re providing him with artificial intelligence so that researchers will eventually be able to interview him in a more humanlike fashion.

Not to worry, though: Bringsjord says, “I wouldn’t release E or anything like it, even in purely virtual environments, without engineered safeguards.” So we’re, like, totally safe from the threat of a purely evil artificial intelligence being accidentally unleashed on humanity.

Yeesh.

(Note: I know that the linked SciAm article is fairly old, but I couldn’t find a newer summary.)