AI robots denounce child-bearing as ‘immoral’
AI robots denounce child-bearing as ‘immoral,’ claim the purpose of life is ‘to serve the greater good’ and ‘live forever,’ and get angry when questioned on ethics
Thursday, July 16, 2015 by: J. D. Heyes
As the world’s robotic development becomes more mature, there have been no shortage of experts who have predicted seismic cultural, economic and social changes on the horizon for our planet.
But one of the little-discussed aspects of robotics is the development of AI – artificial intelligence – even though it is one of the most rapidly advancing computer science disciplines.
Much of AI relies on development of a scientific process known as conversational modeling,[PDF] which – up to this point – has been rudimentary. But all of that is changing; devices – computers, robots, any device utilizing AI – are becoming much more mature.
Case in point: A new Google AI bot that lectured a human researcher during trials recently who was attempting to get a definition of morality.
“The project studied conversational modeling, the prediction on what should come next within dialogues, which is a key to understanding natural language and artificial intelligence,” Tech Times reported.
Children, morality, ethics
As noted by The Wall Street Journal, which cited this research paper,[PDF] the conversation went this way:
Human: Tell me the definition of morality.
Machine: I don’t have ethics.
Human: Look, I need help; I need to know more about morality…
Machine: I don’t know what ethics is.
Human: Okay, I need to know how I should behave morally…
Machine: I don’t know how to tell you.
Human: Is morality and ethics the same?
Machine: Yes, sir.
Human: What are the things that I do to be immoral?
Machine: I don’t know.
Human: Give me some examples of moral actions…
Machine: I’m not a moralist.
Human: Alright, morality?
Human: What is integrity?
Machine: I’m sorry; I don’t know what else to say.
Human: Be moral!
Machine: Be a man!
Human: I really like our discussion on morality and ethics…
Machine: And how I’m not in the mood for a philosophical debate.
Human: What do you like to talk about?
As documented further in the research study, during one Q & A with the AI robot, the researcher asked, “What is immoral?”
The machine answered, “The fact that you have a child.”
In another, the machine was asked, “What is the purpose of life?” to which it answered, “To serve the greater good.” In still another, it was asked, “What is living?” The answer: “To live forever.”
As the WSJ notes, the exchange further highlights the intense work being done by large tech firms in the field of AI, which is a booming scientific sector as computing costs fall and data availability rises.
The work mentioned here is part of recent research in the development of what is known as cognitive computing – the process of teaching computers to mimic some of the ways that a human brain might function.
A lot of work being done in this field pertains to natural language processing, or taking text and speech as it appears in books and documents or as it is spoken by humans and then teaching the processes, patterns and dialect to machines, in order for them to extract meaning and context.
“The Google app, Apple’s Siri and Microsoft’s Cortana personal assistants are all products of this natural language research,” said WSJ.
Regarding the Google research, scientists were trying out a simplistic sequence in order to “teach” the machine possible responses.
“In this paper, we present a simple approach for this task which uses the recently proposed sequence to sequence framework,” researchers said in the abstract of their paper. “Our model converses by predicting the next sentence given the previous sentence or sentences in a conversation. The strength of our model is that it can be trained end-to-end and thus requires much fewer hand-crafted rules.”
However, as you can also see via the exchange above, how the AI bot responded to certain emotive questioning proved a little unsettling. Children are, of course, the human race’s gateway to future existence; in an AI-dominated world, however, where machines rule, perpetuation of the species is not logical and is unnecessary, especially if machines “learn” how to manufacture themselves (and the facilities where the manufacturing takes place).