The appendix discusses consciousness, self awareness, emotions, and free will, but the authors are using strictly behavioral definitions for these terms so they can legitimately model them. They model emotions as having 3 dimensions of pleasure, arousal, and dominance. An agent capable of acting to increase its pleasure has free will. Self awareness means passing the mirror test, recognizing your reflection as you. Collectively, these things make up their definition of consciousness.
It seems reasonable. They ignore the metaphysical aspects, like whether you have an immortal soul that goes to heaven. (You don't). They don't confuse the issue with whether we have a moral obligation to not harm conscious agents. (There is no such rule. Actions are unethical if they make you uncomfortable. That's why cockfighting is illegal in all 50 US states even though we are OK with killing a billion chickens per week for food). ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T32a7a90b43c665ae-M250d25496123a3107c97408a Delivery options: https://agi.topicbox.com/groups/agi/subscription
