Can a crocodile play basketball?
AI’s answer in this age of ChatGPT, 3 different applications:
One: That’s an interesting question. Crocodiles are amazing animals that have been around for millions of years. They are very good at swimming, hunting, and surviving in different habitats. But can they play basketball?
Well, the answer is probably no. Crocodiles are not very good at jumping, running, or handling a ball. They have short legs, heavy bodies, and long tails that make it hard for them to move quickly on land. They also have very strong jaws, but not very flexible hands. They can’t grip a ball or pass it to their teammates. They might even try to eat the ball or the other players!
Two: No, a crocodile cannot play basketball. Crocodiles are reptiles and do not possess the physical abilities or cognitive skills required to play basketball. (Photo by Pixabay)
Three: Crocodiles are not capable of playing basketball due to their anatomy and lack of abilities required for such activities. They are not built for complex motor skills or coordination needed for sports like basketball.
Walter Isaacson wrote in 2005 that the crocodile question stymied AI, which invariably did well with any number-crunching question but not something that involved ‘thinking.’ So said his book ‘The Innovators,’ which traces the development of both computers and the internet. The most significant advance for the former was the microchip, which allowed for computers to shrink to desktop-sized. The most significant advance for the latter was switchable digital packets, allowing computers to communicate with each other over a network.
The first crocodile answer hedges its bets. ‘Probably no,’ it says, and explains why, exploring the crocodile’s anatomy, taking the question quite seriously (rather than giggling it away, as any 4 year old would do).
Answers two and three also don’t realize someone is putting them on, but they are more definitive and give evidence of ‘thinking.’ That is, they draw conclusions from how a crocodile is built in a way that is beyond pure number crunching.
‘The Innovators’ final chapter tells how chess grandmaster Gary Kasparov agreed to a challenge from IBM’s Deep Blue and lost. ‘Yeah, well, it’s just pure number-crunching,’ he comforted himself, not that it made losing to it any better. The machine wasn’t actually thinking. It was just running any given chess board against a gargantuan database it had downloaded, including all grandmaster games, and recalling whether any given move next move had turned out good or bad. Later, he got the idea of working in tandem with AI, letting the machine crunch the numbers whereas the person could focus on the overall deep strategy that was beyond the machine’s capability.
The concept was tested, also in 2005: grandmaster matched against machine against chess amateur paired with computer backup, The grandmasters lost. So did the machines alone. The amateurs with computer-backup were the ones victorious.
So the current crocodile answer isn’t too bad, really. It ‘reasons’ on the reptile’s anatomy to say, ‘No way.’ It doesn’t just search the internet for websites that says if a crocodile can play basketball or not, a method that would return zilch results.
AI prognosticators have christened as the ‘singularity’ the moment AI reaches the point where it doesn’t need people, where it can and does program itself. Will it decide people just get in the way at that point?
Dumping science in our collective lap with no idea as to how to control it is something I have worked into most of my books. From ‘Tom Irregardless and Me:’
“Sam Harris gave yet another TED talk in which he asked: “Can We Build AI Without Losing Control Over It?” The answer is no; you’ll screw it up like you screw up everything, like you drove Albert Einstein to say, “if I had known, I would have become a locksmith.”
From: ‘In the Last of the Last Days: Faith in the Age of Dysfunction:’
“Elon Musk, Steve Wozniak, Andrew Yang, and a panel of other leaders in technology, urged in March 2023 at least a six-month moratorium on AI development, allowing a little time to figure out what its long-term consequences will be. From their open letter of March 2023:
“Advanced AI could represent a profound change in the history of life on Earth and should be planned for and managed with commensurate care and resources. Unfortunately, this level of planning and management is not happening, even though recent months have seen AI labs locked in an out-of-control race to develop and deploy ever more powerful digital minds that no one – not even their creators – can understand, predict, or reliably control.
“… Should we let machines flood our information channels with propaganda and untruth? Should we automate away all the jobs, including the fulfilling ones? Should we develop nonhuman minds that might eventually outnumber, outsmart, obsolete and replace us? Should we risk loss of control of our civilization?
“Events move quickly. Who would ever have thought a major risk to writing a book like this would be that portions would be obsolete by its date of release? Within days of this AI caution came a “photo” of Pope Francis fleeing a bevy of police closing in upon him from all sides. “I asked Wonder App to paint, Pope running from the police,” the banner advertised You could never tell it wasn’t him—even if you did wonder how His Holiness could hustle so fast.”
From ‘I Don’t Know Why We Persecute Jehovah’s Witnesses: Searching for the Why:’
“The New York Times writes about an app that makes it “relatively easy to create realistic face swaps and leave few traces of manipulation. . . . It’s not hard to imagine this technology being used to smear politicians, create counterfeit revenge porn, or frame people for crimes. Lawmakers have already begun to worry about how such deepfakes might be used for political sabotage and propaganda.” The anonymous developer cheerfully helps the Times reporter try his own hand at it. “I’ve given it a lot of thought,” he [says], “and ultimately I’ve decided I don’t think it’s right to condemn the technology itself.”[i] Of course not! They never do. It’s on to the next advance of science! Let the ethicists figure out what he has just dumped in their laps, something “which can of course be used for many purposes, good and bad.” It’s their problem, not his.
“Already, news sources show an eagerness to rely upon unidentified sources that frequently turn out to be wrong. Will they handle this new advance responsibly? Not only must we anticipate dubious proven by video character assassination to become routine, but the more lasting consequence of this new technological advance may be that even genuine video evidence will be dismissed as fake news. It is as Isaiah envisioned: “Ah! Those who call evil good, and good evil, who change darkness to light, and light into darkness, who change bitter to sweet, and sweet into bitter!” The guileless one so slandered will explode in moral indignation, and thus appear guilty as hell. The professional liar will shrug it off with the feigned saddened dismay that his enemies could sink so low.”
Which will come first: Will humans succeed in harnessing their science so as not to ruin them all? Or will the NBA begin drafting crocodiles?
****** The bookstore