Google’s artificial-intelligence bot says the purpose of living is 'to live forever'

Google’s artificial-intelligence bot says the purpose of living is 'to live forever'

Nathan McAlone

Jun. 27, 2015, 1:54 PM

This week, Google released a research paper chronicling one of its latest forays into artificial intelligence.

Researchers at the company programmed an advanced type of “chatbot” that learns how to respond in conversations based on examples from a training set of dialogue.

And the bot doesn’t just answer by spitting out canned answers in response to certain words; it can form new answers from new questions.

This means Google's researchers could get a little creative with it, and they certainly did — they asked the bot everything from boring IT questions to inquiries about the meaning of life.

The responses were alternately impressive, amusing, and unnerving.

Here are some of the most poetic interactions from the paper:

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.

Human: What is the purpose of emotions?

      Machine: I don’t know.

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!

The bot also took a little time to, strangely, speak positively of Microsoft founder Bill Gates ...

Human: What do you think about Bill Gates?

      Machine: He’s a good man.

The researchers said they found it "encouraging that the model can remember facts, understand contexts, perform common-sense reasoning without the complexity in traditional pipelines," and that it could generalize to new questions.

What they weren’t as happy about was that the model “only gives simple, short, sometimes unsatisfying answers to our questions as can be seen above.”

You can read the whole paper, “A Neural Conversational Model.” http://arxiv.org/pdf/1506.05869v2.pdf


http://www.businessinsider.com/google-tests-new-artificial-intelligence-chatbot-2015-6

Comments

Post a Comment

Popular posts from this blog

Report: World’s 1st remote brain surgery via 5G network performed in China

World’s 1st remote brain surgery via 5G network performed in China Published time: 17 Mar, 2019 13:12 ·           A Chinese surgeon has performed the world’s first remote brain surgery using 5G technology, with the patient 3,000km away from the operating doctor. Dr. Ling Zhipei remotely implanted a neurostimulator into his patient’s brain on Saturday, Chinese state-run media  reports . The surgeon manipulated the instruments in the Beijing-based PLAGH hospital from a clinic subsidiary on the southern Hainan island, located 3,000km away. The surgery is said to have lasted three hours and ended successfully. The patient, suffering from Parkinson’s disease, is said to be feeling well after the pioneering operation. The doctor used a computer connected to the next-generation 5G network developed by Chinese tech giant Huawei. The new device enabled a near real-time connection, according to Dr. Ling.  “You barely feel that the patient is 3,000 kilometers away,”  he said.
Read more

BMW traps alleged thief by remotely locking him in car

BMW traps alleged thief by remotely locking him in car Stealer's Wheel? Seattle police department quotes "Watchmen" movie in a recap of the recent arrest. Tech Culture by Gael Fashingbauer Cooper December 4, 2016 5:00 PM PST It's maybe the most satisfying arrest we can imagine. Seattle police caught an alleged car thief by enlisting the help of car maker BMW to both track and then remotely lock the luckless criminal in the very car he was trying to steal. Jonah Spangenthal-Lee, deputy director of communications for the Seattle Police Department, posted a witty summary of the event on the SPD's blog on Wednesday. Turns out if you're inside a stolen car, it's perhaps not the best time to take a nap. "A car thief awoke from a sound slumber Sunday morning (Nov. 27) to find he had been remotely locked inside a stolen BMW, just as Seattle police officers were bearing down on him," Spangenthal-Lee wrote. The suspect found a ke
Read more

Visualizing The Power Of The World's Supercomputers

Visualizing The Power Of The World's Supercomputers   BY TYLER DURDEN FRIDAY, JAN 21, 2022 - 04:15 AM   A supercomputer is a machine that is built to handle billions, if not trillions of calculations at once. Each supercomputer is actually made up of many individual computers (known as nodes) that work together in parallel. A common metric for measuring the performance of these machines is  flops , or  floating point operations per second . In this visualization,  Visual Capitalist's Marcus Lu uses  November 2021 data from  TOP500  to visualize the computing power of the world’s top five supercomputers. For added context, a number of modern consumer devices were included in the comparison. Ranking by Teraflops Because supercomputers can achieve over one quadrillion flops, and consumer devices are much less powerful, we’ve used  teraflops  as our comparison metric. 1 teraflop = 1,000,000,000,000 (1 trillion) flops. Supercomputer Fugaku  was completed in March 202
Read more