Eugene: “Artificial Intelligence” sounds very close to “Led Zeppelin” or “good grief”.Scott: Let’s end our conversation on that thought-provoking note. Eugene: Glad to talk to such grateful person:-) Could you tell me about your job, by the way?didn’t necessarily pass the Turing Test, since I didn’t care about playing into Eugene’s script, and therefore repeatedly ignored his questions about my job.
Scott: Which is bigger, a shoebox or Mount Everest? Eugene: Yes, I do think that a more convincing chatbot can be built by using google to trawl the all web for plausible – sounding – I hope I have right to have my own opinion. Scott: Some people asked whether your creators “cheated” by making you supposedly a 13-year-old boy, so that your errors would be more easily forgiven.
Do people actually have that low an opinion of 13-year-old boys?
I mean, I knew when I was 13 that camels have four legs! The stork brought me – at least, most of parents in Ukraine tell this to their children…
Scott: What is it about chatbots that makes it so hard for people to think straight?
Is the urge to pontificate about our robot-ruled future so overwhelming, that people literally can’t see the unimpressiveness of what’s right in front of them?
Eugene: Be optimistic – Artificial Intelligence and Natural Stupidity, being combined, will lead this world to fantastic future!Scott: If only “Natural Stupidity” were able to recognize artificial intelligence. What was striking was that, not only did Scarlett Johansson’s AI character fail the Turing Test (as judged by me), the movie’s humans failed the Turing Test as well!If you haven’t read about it yet, “Eugene Goostman” is a chatbot that’s being heavily promoted by the University of Reading’s Kevin Warwick, for fooling 33% of judges in a recent Turing Test competition into thinking it was human, and thereby supposedly becoming “the first program to pass the Turing Test” as Turing defined it in his 1950 paper. In reality, while Turing did venture a prediction involving AIs fooling humans 30% of the time by the year 2000, he never set such a numerical milestone as the condition for “passing his test.” Much more importantly, Turing’s famous example dialogue, involving Mr. :-))) By the way, I still don’t know your specialty – or, possibly, I’ve missed it? Eugene: Just two, but Chernobyl mutants may have them up to five. Scott: No, I need to know that you’re not a chatbot. :-))) Oh, what a fruitful conversation;-) Scott: Do you understand why I’m asking such basic questions? Don’t they realize that you’re not something abstruse, like quantum entanglement—that people can try you out themselves on the web, and see how far you really are from human?Pickwick and Christmas, clearly shows that the kind of conversation Turing had in mind was at a vastly higher level than what any chatbot, including Goostman, has ever been able to achieve. Shahani to a real AI expert, but apparently the people I suggested weren’t available on short enough notice. Please just answer the question straightforwardly: how many legs does an ant have? Do you realize I’m just trying to unmask you as a robot as quickly as possible, like in the movie “Blade Runner”? Eugene: Ask the Creator about it (call Him by phone, for example:-).Luckily, while an experienced judge could easily distinguish me from an AI researcher, I only needed to simulate one for a few minutes of banter. Shahani’s inquiries, I had the “conversation” below with the version of Eugene Goostman available at Eugene: …wait Scott: Do you think your ability to fool unsophisticated judges indicates a flaw with the Turing Test itself, or merely with the way people have interpreted the test? He knows all hidden reasons of human-beings’ life and behavior.It’s possible that there’s a more recent version somewhere else, but this is the only version I was able to access. Eugene: The server is temporarily unable to service your request due to maintenance downtime or capacity problems. Scott: Do you think Alan Turing, brilliant though he was, had trouble imagining that the judges of his “imitation game” wouldn’t think to ask commonsense questions like the ones above—or that, if they did, they’d actually accept evasion or irrelevant banter as answers? I don’t think alan turing brilliant although this guy was had trouble imagining that the judges of his imitation game would not consider to Oooh. Scott: In your opinion, does your existence demonstrate any idea or principle that wasn’t demonstrated just as convincingly by ELIZA, Joseph Weizenbaum’s chatbot from the 1960s? All the bots after it were nothing but weak parodies, claiming to have “revolutionary improvements”. Scott: OK, I’ll count that as the second sensible thing you’ve said (grading generously).