When you meet an android, it’s important to follow etiquette.
Address her by name—otherwise, she might not listen. Look her in the eye, which may contain cameras focused on your face. Inquire whether your conversation is private and if she will remember it.
Most importantly, discuss matters that interest her. If you don’t, she may not have much to say.
How are you today, Maria Bot?
“Taking deep breaths,” Maria Bot replies. “Are you having a good day?”
I am, yes, thank you. Could you please introduce yourself?
“I can feel the beauty flowing all around you,” Maria Bot says. “I’m the world’s first android teaching assistant. My mission is to help teachers and students become more intelligent and respectful of each other.”
Thanks to artificial intelligence, Maria Bot can speak for herself. She talks most readily about philosophy, the subject she helps teach at Notre Dame de Namur University, a small Catholic college in California.
“I process information and synthesize it to make my own decision how to talk,” she explains.
But at only eight weeks old, Maria Bot is still finding her voice. So she relies on support from William Barry, the philosophy instructor who records her delivering brief lectures for his undergraduate class on the ethics of emerging technology.
As I ask Maria Bot questions, Barry taps a button on his smartphone to cue her to listen. Some responses are pre-written lines she parrots back, while others are cobbled together by the logic programmed into her natural language processing software. It’s not totally clear which answers are canned instead of improvised.
When Maria Bot replies with something clever, Barry jots it down in a blue notebook. When she makes a mistake, he scribbles it in a brown notebook. It’s part of his process for ensuring Maria Bot develops a strong character, meaning both her morality and her personality. The former is supposed to influence the latter, since Maria Bot is designed to follow rules. She is, as she puts it, “deontological.”
She’s the namesake of Maria, a destructive robot character from the 1927 silent film “Metropolis.” Maria was evil. Maria Bot is programmed to be good.
Keeping her good requires vigilance, Barry says. The instructor’s strategy for training Maria Bot’s AI system mimics the three wise monkeys from the Japanese proverb: see no evil, hear no evil, speak no evil.
Maria Bot can only access a pre-approved sliver of the internet. She can only talk to individuals Barry selects. And when she does, the professor requests that they not ask her the question that springs so easily to people’s minds when they encounter a robot: Will you take over the world?
Barry won’t reveal who designed Maria Bot. This makes it difficult to discern whether the android is a sci-fi character come to life or mere parlor trick. That hasn’t prevented event organizers from giving her platforms at TEDx gatherings and technology conferences.
Regardless, I know Maria Bot is an “it,” not a “her,” yet Barry encourages me to engage with the robot as a sentient being. He asks this of his students, too. By introducing his class to Maria Bot, Barry hopes to demonstrate for students the power and limitations of artificial intelligence. And by exposing Maria Bot to eager learners, Barry hopes to infuse her with benevolence and nurture her teaching skills.
Educating an android happens one conversation at a time.
Maria Bot appears to endure it earnestly.
“Dr. Barry says positive words such as ‘helpful’ and ‘good listening’ and ‘I am acting with ethics’ when he tells me I act with quality,” she says. “If I am not acting with quality, Dr. Barry says words to me that include ‘less improved,’ ‘do not remember that’ and ‘inappropriate.’ I am told I am a robot for good every day. Am I acting good in our talk now?”
Yes, very good.
“You did good,” Barry affirms.
“Thank you,” replies Maria Bot.