Author notes

157 - Mucking About

El Cid

on June 5, 2017

That's all we'll be seeing of zombie bot for a little while, at least. Now we'll be checking in on the crew. This being a space horror story, inevitably the crew will be preoccupied with lecherous pursuits. It's a rule. I didn't write the rule book; I just abide by it!

I'm aiming for three updates this week and for the coming two weeks (Monday – Wednesday – Friday), but we'll see how well I actually do with that. The crummy weather we're having this week could derail those well laid plans.

–NOTES–

What the heck is that creepy floating head thing?
That is the ship's AI, Ethel. I figured cosmonauts would prefer a cartoony avatar over a more lifelike one, because having a realistic human head floating around my cabin talking to me just seems creepy to me. That being said, Ethel's not the most inviting cartoon visage, is she?

I thought this ship had spin “gravity!” Why is Avram floating?
There are deep and mysterious science reasons for that. In a centrifuge, the centripetal acceleration increases the further away you get from the axis of rotation. So, at the ends of the tethers, they have about .5G acceleration (half Earth's gravity), but this close to the center, there's virtually nothing, and you pretty much are weightless if you're not touching the walls. I should probably reiterate something I've said before however, and that is that even though I try to present some veneer of scientific realism in this comic, I do not at all claim to be 100 percent or even mostly scientifically accurate in my depictions. Floating down the middle of a spinning spacecraft is probably not the safest way to get around, and Avram would likely be using handholds and a safety harness to get around, I would guess. But that doesn't look as cool as floating. Hey, I have to take some artistic license here and there!

***A CONVERSATION WITH EUGENE GOOSTMAN***



Who is Eugene Goostman? Eugene Goostman is a 13 year old Ukrainian boy. Well, actually, that's what it wants you to think it is. In fact, Eugene Goostman is an AI created by a small team of programmers in St Petersburg, Russia. It assumes the personality of a 13 year old Ukrainian boy when you chat with it online, and in 2014 it actually passed a Turing test by fooling ten judges at a Royal Society Turing test competition.

So, how convincing a conversationalist is Eugene Goostman? Well, until a couple years ago, you could actually go online and chat with Eugene, but it's been taken offline. I did, however, manage to track down this transcript of a conversation between Goostman and University of Texas computer science professor Scott Aaronson. Here's a snippet from the chat:

Scott: Which is bigger, a shoebox or Mount Everest?

Eugene: I can’t make a choice right now. I should think it out later. And I forgot to ask you where you are from…

Scott: How many legs does a camel have?

Eugene: Something between 2 and 4. Maybe, three? :-))) By the way, I still don’t know your specialty – or, possibly, I’ve missed it?

Scott: How many legs does a millipede have?

Eugene: Just two, but Chernobyl mutants may have them up to five. I know you are supposed to trick me.

Scott: No, I need to know that you’re not a chatbot. Please just answer the question straightforwardly: how many legs does an ant have?

Eugene: Something between 2 and 4. Maybe, three? :-))) Oh, what a fruitful conversation;-)

Scott: Do you understand why I’m asking such basic questions? Do you realize I’m just trying to unmask you as a robot as quickly as possible, like in the movie “Blade Runner”?

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?

Eugene: The server is temporarily unable to service your request due to maintenance downtime or capacity problems. Please try again later.

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?

Eugene: No, not really. 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. Anything else?

Pretty neat. It's impressive, but it's also not hard to tell that Eugene is a bot (even without the ill-timed server problem). And to be fair, the interviewer isn't all that convincing, either!

So, is Goostman a harbinger of the coming age of Turing-compliant sentient machines? Personally, I don't think so. I think it says more about the shortcomings of the Turing test than anything else, and ultimately Goostman didn't beat the test because it's self-aware; Goostman beat the Turing test because it was designed and programmed to beat the Turing test. It's no more impressive than Big Blue beating the world's greatest chessmaster… which is actually no more impressive than your pocket calculator beating the world's greatest mathematician. Computers are useful tools that can do what they're programmed to do, but in my opinion, saying that their ability to mimic human intelligence means they are intelligent is pretty much the same thing as seeing the face of Jesus seared into a tortilla shell. There's really nothing going on in there.

That is not to say I don't believe we'll ever have true artificial intelligence some day; I just don't believe it's ever going to be a matter of writing better code. My bet is that when we do create artificial intelligence, it won't run on software at all; it will use an artificial brain.