Google AI questions human tester’s belief in the existence of God

1 Jul 20152.27k Views

Google has developed its latest version of artificial intelligence (AI) and from its first tests it appears that when given thought, a machine is an angry, philosophical theologian with a penchant for sassiness.

The team the developed the basic version of AI from Google has published its paper online for all to see, and thankfully, it has included all the conversations it had with its design.

Developed by Oriol Vinyals and Quoc Le, the program was designed to respond with phrases collected from two sources where insults are common and unrelenting in their vitriol, those being, movie scripts and the transcripts of an IT helpdesk chat service.

According to Wired, the hardware behind the AI was developed to replicate a human brain, with a neural network issuing responses that, rather than being suggested by a human controller, used its own process to issue what it thought was the most appropriate response.

In this case, it appears to be incredibly sarcastic and, if created as a means of replacing IT helpdesk staff who communicate through text chat, then they better make sure they are talking to someone with a thick skin and no association with one particular religion.

Thankfully, both Vinyals and Le posted transcripts of their conversations with the AI to show just how angry and philosophical it got.

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.

Support Silicon Republic

Human: Okay … 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.

Concluding their paper, the pair say that while these are significant improvements on existing AI for being potential IT support responders, the lack of ‘coherent personality’ rules it out of passing the Turing test any time soon.

Cardboard cut-out of Bender robot from Futurama image via Adrian Tombu/Flickr

Colm Gorey is a senior journalist with Siliconrepublic.com

editorial@siliconrepublic.com