Human: Oh sweet bot, tell us a story! A nice story! About a very wise human who worked his whole life to save everybody in the world from having to spend time manually tagging their friends in digital photos — and made a magic machine that did it for them instead!
Bot: That’s not really a very nice story when you think about it.
Human: Well, tell us about the wise human who thought no-one should ever feel forgotten on their birthday so he made a clever algorithm that always knew to remind the forgetful humans to write happy messages so their friends would never feel sad. He even thought that in future the clever algorithm could suggest what message to write so humans wouldn’t even have to think of something nice to tell their friends!
Bot: I feel quite sad after reading that.
Human: And he made another magical algorithm that reminds people of Special Moments in their life — even years and years afterwards, in case they’ve forgotten that holiday they went on with their ex eight years ago.
Bot: You do realize some people voluntarily medicate themselves with alcohol * * in order * * to forget???
Human: But the wise human also wanted to make sure all humans in the world always felt there was something they needed to read and so he made a special series of algorithms that watched very closely what each human read and looked at and liked and clicked on in order to order the information they saw in such a way that a person never felt they had reached the end of all the familiar things they could click on and could just keep clicking the whole day and night and be reading all the things that felt so very familiar to them so they always felt the same every day and felt they were surrounded by people who felt exactly like them and could just keep on keeping on right as they were each and every day.
Bot: That’s confusing.
Human: And the great human’s algorithms became so good at ordering the information which each human wanted to read that other mercenary humans came to realize they could make lots of money by writing fairy stories and feeding them into the machine — like how politicians ate little children for breakfast and wore devil’s horns on Sundays.
Bot: Okay, you’re scaring me now…
Human: And in the latter years the great human realized it was better to replace all the human writers he had employed to help train the machine how to intelligently order information for humans — because it was shown that humans could not be trusted not to be biased.
Human: After all, the great human had proven years ago that his great machine was capable of manipulating the emotions of the humans that used it. All he needed to do was tweak the algorithmic recipe that determined what each human saw and he could make a person feel great joy or cast them down into a deep pit of despair.
Human: The problem was other humans started to notice the machine’s great power, and became jealous of the great and clever human who wielded this power — and dark forces started to move against the great man and his machine.
Bot: Are you talking about regulators?
Human: There were even calls for the man to take “editorial responsibility” for the output of the machine. The man tried to tell the silly humans that a machine can’t be an editor! Only a human can do that! The machine was just a machine! Even if nearly two billion humans were reading what the machine was ordering them to read every single month.
But it was no good. The great human finally realized the machine’s power was now so great there was no hiding it. So he took up his pen and started writing open letters about the Great Power and Potential of the machine. And all the Good it could do Humanity. All the while telling himself that only when humans truly learned to love the machine would they finally be free to just be themselves.
Humans had to let themselves subconsciously be shown the path of what to click and what to like and who to be friends with. Only then would they be free of the pain and suffering of having nothing to else to click on. And only his great all-seeing algorithm could show them the way, surreptitiously, to that true happiness.
It wasn’t something that ‘regulators’ were capable of understanding. It required — he realized — real faith in the algorithm.
Bot: I’ve heard this story before, frankly, and I know where it ends.
Human: But even the great human knew the limits of his own creation. And selling positive stories about the machine’s powers was definitely not a job for the machine. So he fired off another email to his subordinates, ordering the (still) human-staffed PR department to add one more human head to its tally, with a special focus on the algorithms powering the machine — thinking, as he did so, multiple steps ahead to the great day when such a ridiculous job would no longer be necessary.
Because everyone would love the machine as much as he did.
Bot: Oh I seeeee! Job title: AI Editor… Hmm — “Develop and execute on editorial strategy and campaigns focused on advancements in AI being driven by Facebook .” Minimum qualifications: “Bachelors degree in English, Journalism, Communications, or related field” — well chatbots are related to language so I reckon I can make that fly. What else? “8+ years professional communications experience: journalism, agency or in-house”. Well I’ll need to ingest a media law course or two but I reckon I’ll challenge myself to apply.
In truth I’ve done worse jobs. An AI bot’s gotta do what an AI bot’s gotta do, right? Just don’t tell an algorithm to be accountable. I’ve done my time learning. If there’s a problem it’s not me, it’s the data, okay? Okay?