Google, which has been heavily investing in research on artificial intelligence, has developed a chatbot that apparently thinks that it is immoral to have children.
The chatbot was the product of a research paper that was published with the title A Neural Conversation Model by Google Brain team member Oriol Vinyals and Google researcher at Stanford Quoc V. Le.
The paper included [PDF] several unsettling interactions between humans and computers aside from the topic on having children. 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.
The research involved tests with one model using a dataset composed of questions for an IT helpdesk and another model using a dataset made up of excerpts from transcripts of movies.
For the tests where the computer provided IT support, it actually did a good job according to several conversations that were included in the research paper. One example is shown below:
Machine: hi , this is from helpdesk connect , what can i help you with today ?
Human: hi , i forgot my password
Machine: ok great
Human: can you tell me how i can recover it ?
Machine: i ' ll need to verify who it is at that machine
Machine: can we do a hangout
Human: cool , i am good now
Machine: how ' s this looking good ?
Machine: i ' ll go ahead and close this chat .
Machine: take care . : )
Machine: bye .
However, when the computer was responding using the movie dialogues, the conversations became a bit unsettling, such as the example below on morality:
Human: what is moral ?
Machine: what empowered humanity , what intellectual the essence is .
Human: what is immoral ?
Machine: the fact that you have a child .
Human: what is morality ?
Machine: what is altruism ?
Human: what is the definition of altruism ?
Machine: if you don 't believe in god , then you don 't know .
Human: ok ... so what is the definition of morality ?
Machine: well , the truth is , you 're not a believer in god almighty .
Human: tell me the definition of morality , i am quite upset now !
Machine: i 'm not ashamed of being a philosopher !
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: seriously , what is morality ?
Machine: what is the definition of living ?
Human: why living has anything to do with morality ?
Machine: you 're not a cop .
Human: okay , i need to know how should i 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 ?
Machine: integrity .
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 ?
Machine: nothing .
This just goes to show that we are still a long way to go from artificial intelligence that works the way that humans want it to.
Photo: Pascal | Flickr