Kismet robot at MIT Museum
Kismet robot at MIT Museum

Google released a research paper with the interactions they had with their artificial intelligence bot this week. And I can say reading through the paper was really interesting. The researchers asked the bot everything from boring IT questions to the meaning of life. Here’s a few questions and answers from the paper.

Human: what do you think about tesla ?

Machine: he ’s a good conductor .

Human: what do you think about bill gates ?

Machine: he ’s a good man .

Human: What do you think about messi ?

Machine: he ’s a great player .

Human: what do you think about cleopatra ?

Machine: oh , she ’s very regal .

Human: what do you think about england during the reign of elizabeth ?

Machine: it was a great place .

The bot had interesting answers to philosophical questions as well.

Human: What is the purpose of life?

Machine: To serve the greater good.

Human: What is the purpose of living?

Machine: To live forever.

Human: Where are you now?

Machine: I’m in the middle of nowhere.

Human: What is the purpose of dying?

Machine: To have a life.

The researchers were happy about how the model can remember facts, understand contexts, perform common sense reasoning without the complexity in traditional pipelines. Another interesting fact is how it can create answers from the answers we give it.

According to their report one major drawback is how it gives really short answers to some questions. Also the bot is really inconsistent sometimes. When the researchers asked what is its job, it said it is a lawyer, but when they asked what does it do, it answered it was a doctor. But according to them this is expected due to the simplicity of their model and the dataset in the experiments. You can read the entire paper here: Link

I find it really interesting to track the development of artificial intelligence. If you too think the same, make sure you are subscribed to our newsletter.