Researchers have shown that machines are inching closer to self-learning, and perhaps even copping a little attitude.
Over at Google GOOGL -0.66%, a computer program using a database of movie scripts was asked again and again by researchers to define morality. It struggles to do so, and in a conversation recorded by its human engineers, becomes exasperated and ends the conversation by lashing out at its human inquisitor.
Here’s part of the exchange, as related in a paper presented this week:
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?
The exchange sheds further light on the latest work carried out by large technology firms in the field of artificial intelligence, a booming field as data availability rises and computing costs plummet. This specific work is part of recent developments in what’s known as cognitive computing – teaching computers to mimic some of the ways a human brain works. Much work in this field is being done in natural language processing – taking text or speech as it spoken by humans or as it appears in books and documents and teaching machines to extract meaning and context from it. The Google app, Apple’s Siri and Microsoft’s Cortana personal assistants are all products of this natural language research.