Forget AI Singularity; These Are the Real AI Risks Facing Us, Now!

Singularity is a myth with excellent production values: a clean villain, a clean apocalypse, and a clean date on the calendar. Reality is messier and less cinematic, a slow transfer of wealth, a quiet erosion of privacy, and a data center draining a town’s water supply.

It is a seductive story. It is also, on the evidence, nonsense. And the energy the public spends fearing a robot apocalypse that isn’t coming is energy stolen from the much duller, much more urgent work: dealing with the AI harms that are already here, doing damage, on this very planet, this very year.

Between myth and reality

We do not need to resort to the fertile imaginary history of science fiction, where visionary creative minds started envisioning a world where the “intelligent machine” takes over the free will of humans. Where we can go back as early as 1772, when Joseph Wright of Derby created his painting called “An Iron Forge.” Or maybe 100 years after that, when Victorian author Samuel Butler penned three chapters titled “The Book of the Machines” in his novel called “Erewhon” in 1872, which was developed from his own essay, written nine years earlier under the title “Darwin among the Machines.”

We do not even need to go back to Karel Čapek, the Czech playwright, in his 1920 play titled “Rossum’s Universal Robots,” in which he coined the term “Robot,” from its linguistic source in the Czech language, “robota,” which actually means “Forced Labor.”

Nor to go through the early 20th-century cinematic productions that artistically depicted the same concept, starting in the silent serial “The Master Mystery” (1918), where the first humanoid robot was ever depicted on the screen. Or the Italian silent film “Il Uomo Meccanico” (1921), where the first robot vs. robot fight was ever filmed. Or the French sci-fi movie “L’Inhumaine” (1924), where a woman called Claire is resurrected by her lover scientist, by forcing her heart to beat and her “free” will restructured by a machine to make her capable of love and human-like empathy again.

We will try to stick to reality, even though creative imagination expectedly preceded it, and it is indeed very tempting.

In 1965 the mathematician I.J. Good coined the idea of an “intelligence explosion”: a sufficiently clever machine could design an even cleverer successor, which would design a cleverer one still, in a runaway loop that would leave human intelligence far behind. It was a clean thought experiment.

In 1993, it became a movement when the science fiction writer and mathematician Vernor Vinge popularised the term “singularity” for this coming rupture in history, a point beyond which the future becomes, by definition, unknowable.

Ray Kurzweil spent the next ten years turning Vinge’s essay into a franchise, his 1999 book “The Age of Spiritual Machines” and especially his 2005 bestseller. The concept was popularised in a general audience with the publication of “The Singularity Is Near,” which argued that computing power follows an inescapable exponential curve, and superintelligent machines could be achieved by simply extending that trend on the graph.

He set a date of 2029 for when machines would pass the Turing test, and Google later employed him as a director of engineering, thus giving the prediction a corporate endorsement that it had not actually earned through science. By 2007, true believers had begun to gather at the annual “Singularity Summits” in San Francisco, and MIT roboticist Rodney Brooks compared the........

© New Eastern Outlook