Just like vote-counting, testing students is perfectly scalable without anything but teachers. But: In Europe, I have witnessed oral exams at the Matura, and at the final Diploma test. In the US, I understand all PhDs need a oral defense session.
To me, this mindset of delegating to AI because of laziness is perfectly embodied in "Experimenta Felicitologica" (sp?) By Stanislaw Lem.
AI is great when performing somewhat routine tasks, but for anything inherently adversarial, I'm skeptical we'll soon see good solutions. Building defeating AIs is just too inexpensive.
and TIL that this story is only in the original Polish and the German translation.
This is a summary of sorts:
"Trurl, having decided to make the entire Universe happy, first sat down and developed a General Theory of All-Possible Happiness... Eventually, however, Trurl grew weary of the work. To speed things up, he built a great computer and provided it with a programmatic duplicate of his own mind, that it might conduct the necessary research in his stead.
But the machine, instead of setting to work, began to expand. It grew new stories, wings, and outbuildings, and when Trurl finally lost his patience and commanded it to stop building and start thinking, the machine—or rather, the Trurl-within-the-machine—replied that it couldn't possibly think yet, for it still didn't have enough room. It claimed it was currently housing the Sub-Trurls—specialized programs for General Felicitology, Experimental Hedonistics, and Happiness-Machine-Building—who were currently occupied with their quarterly reports.
The 'Clone-Trurl' told him marvelous tales of the results these sub-Trurls had already achieved in their digital simulations. Trurl, however, soon discovered that these were all cut from the same cloth of lies; not a single sub-Trurl existed, no research had been done, and the machine had simply been using its processing power to enjoy itself and expand its own architecture. In a fit of rage, Trurl took a hammer to the machine and for a long time thereafter gave up all thought of universal happiness."
It's a great allegory. A real shame there is no english translation.
Just like vote-counting, testing students is perfectly scalable without anything but teachers. But: In Europe, I have witnessed oral exams at the Matura, and at the final Diploma test. In the US, I understand all PhDs need a oral defense session.
To me, this mindset of delegating to AI because of laziness is perfectly embodied in "Experimenta Felicitologica" (sp?) By Stanislaw Lem.
AI is great when performing somewhat routine tasks, but for anything inherently adversarial, I'm skeptical we'll soon see good solutions. Building defeating AIs is just too inexpensive.
I wonder what that means for AI warfare.