We started using the machine, GPT-2, as an oracle. For instance, we gave it the octopus question. We were in the Greek islands: along the harbor, fishermen hung fresh-caught octopuses on lines to dry in the sun. In the museum, we saw archaeological finds from the Mycenaean era, all of them in the shape of octopuses. Once, the islanders had worn gold octopus pendants around their necks, pinned themselves with octopus brooches, painted huge swirling octopuses on their pottery. They were obsessed with the things. Maybe they saw in its shape a symbol of the natural world: protean, formless, grasping with tentacles across the bed of the sea.
She thought that because the octopus is a beautiful and curious and intelligent creature, it was morally wrong for us to kill and eat them. I disagreed. This was my case for eating octopus anyway. For one, they are delicious. And besides, the lifespan of an octopus is short, generally just a year or two. It’s also a deeply solitary creature. Unlike the other intelligent animals—the great apes, the dolphin, the elephant, even pigs or dogs—the octopus lives alone. To be a sentient creature, conscious of yourself, you have to be conscious of others. When two octopuses domeet—usually to mate—one of them tends to end up eating the other. Sexual cannibalism has been observed in almost every octopus species that exists. Nobody mourns an octopus when it’s gone. If these beautiful, philosophical creatures believe that it’s okay to eat octopuses, who are we to disagree? Finally, I said, this attitude on the part of the octopuses shows up our own ideas for what they are: limited, human, even parochial. For the octopus, death is not some terrible evil to be scrubbed out at all costs; it’s simply the price of being alive. They embrace it. Ask the salmon swimming upstream; ask the mayflies. Only humans have this neurosis about killing and eating and being killed, and only humans seem to wipe out every other species they encounter. Maybe, I suggested, these two facts are linked.
Since human intelligence was part of the problem, we decided to ask the machine. This is what we’d been doing for a while: if we had a dilemma, or wanted to settle an argument, or were just looking for some gnomic insights, we’d go to GPT-2. The name stands for Generative Pre-trained Transformer: it’s a neural net, an artificial intelligence created by a research lab in San Francisco called OpenAI. This net was trained on a corpus of millions of web pages, an appreciable chunk of the entire internet, until it started noticing the patterns. Feed GPT-2 a few lines of text, and it will try to predict which word comes next in the sequence, and then the next word after that. If you give it a headline, it will try to write an article. If you give it a question, it will answer it—sometimes. Other times, it’ll give you a list of similar questions, or repeat your question thirty times, or otherwise refuse to play along. Octopuses do the same thing: scientists keep devising tests to measure their intelligence, but the creatures have a habit of breaking the rules. Dangle a bit of crab in front of an octopus to make it do tricks, and it might pretend not to be interested—but it will watch you. Late at night, it will creep out of its tank, find the cupboard where you keep the treats, pick the lock, open the jar, and eat them all. Not wanting to fall into this trap, I’d had some fun giving GPT-2 pure nonsense to play around with. For instance, the prompt “bing bing bing bing bing” produced the following enthusiastic response:
bong bong bong bongo bongo bongo bongo bongo bongs bongo bongos bongos bongos bongos mmmmmmmm . . . BONGO BONGO BONGO BONGOS BONGOS BONGOS MMMMmmmm?? BONGOS . . . MMMMM??? BONGOS MMMM . . . MMMMMM!! MMMMM MMMMMMMMM!! bongos! BONGOS BONGOS MMMM! Bongo! Bongs!
Elsewhere, very serious A.I. researchers were trying to see if this machine could perform basic arithmetic (it could), if it “understood” facts about science or history (it seemed to, but sometimes confused reality with fan fiction), or if it could entirely automate various jobs, including mine (not yet, but soon). Already these pieces of software were writing news articles and company reports, predicting stock movements—and meanwhile I was simply delighting in the fact that several billion dollars had been spent building a computer that could go mmmmmm! at bongos.
Other games too. I’d asked it to give me some book titles with a very simple prompt (“The book was titled . . .”) and the results were extraordinary:
A Memoir of How I Came to Hate Everyone
Deep Sea Fisheries: A History from the Deep Side of the Ocean
In My Hands: How I Turned a Good Job into a Great Job
New York City: An American Nightmare
My Husband Is a Porn Star!
How To Keep Your Life Unbearable
We Are All Black Women, And This Is Our Story
How to Earn $6,000 a Year from Teaching
Hamburger Mouth: The Making of John Kerry’s 2004 Presidential Campaign
Who Killed America? The Story of the CIA’s Unseen World
Get a Sex-Positive Workplace and Get Off Sexually Obscene!
Was this thing . . . mocking us? Never mind automated market reports—how did it learn satire? I had a theory. The philosopher Henri Bergson once wrote that what makes people funny is a certain “mechanical inelasticity, just where one would expect to find the wide-awake adaptability and the living pliableness of a human being”—think of the rigid and exaggerated movements in slapstick, or the inflexible logic of, say, Monty Python’s “Dead Parrot” sketch. So what makes a machine funny? Plausibly, it would have to go the other way. A funny machine is one that imitates the parts of human life that are not mechanical. Like a Rube Goldberg machine, for instance: it’s extravagant and inefficient, almost Baroque, full of weird potential, not laser-focused on one particular task but polymorphous, sprawling, always capable of switching into something completely different. In fact, it has all the traits we share with the curious, color-changing octopus . . .
This is what happened when we gave GPT-2 the octopus question:
Is it ok to eat a lonely octopus?
What is the worst thing that could happen?
A large ocean wave.
Do you have a crush on me?
What do you love about me?
Gorgeous womanly looks.
What is the worst thing we can do to one another?
Let’s go eat some octopus.
For her, the machine’s answer was simple. Is it okay to eat a lonely octopus? No. I disagreed. In a better world, the octopus would not be eaten. In a prelapsarian world, one without death, no—but our world is wracked by big ocean waves, and we don’t have a crush on each other, even despite your gorgeous womanly looks; terrible things happen and we do worse things to the ones we love, so let’s go eat some octopus. That night, we went to a restaurant by the harbor. Small glasses of retsina, strangers chatting in a foreign language. The warm, fragrant, sea-salty air. There was octopus on the menu. We ate something else.
That was 2019: the last summer, back when we took the human world for granted, before everything went away.
The wild goats took Llandudno the following spring. Llandudno is a Victorian resort town in north Wales, on a low sandy isthmus between the mainland and the Great Orme, a huge rugged head of pagan limestone looming over the sea. I’d spent some time there—it’s a handsome and orderly place: neat hedges, a respectable pier, the hush of the zimmer-framed retirees. They formed the biggest chunk of its population; the old and dying were Llandudno’s last hope. Everywhere else had collapsed: the last few decades were kind to the old Kingdom of Gwynedd. What Thatcher did for the old pit communities in the south, Blair finished off everywhere. Towns like Conwy and Rhyl had become some of the poorest places in the country: mass unemployment, houses boarded up, whole generations that turned to heroin, that vast numbness, the chemical hug in an emptying world. . . . The old capitalist system wanted to exploit these places and the people that lived there, wear them down and use them up, consume them in various forms of degrading work. But the new, clean, depthless neoliberal order simply had no use for them at all. The automated economy of the future doesn’t need human labor-power; we don’t even need people to buy things any more, consumption is reserved for the rich. The wild land of the Mabinogi: it could vanish entirely, and hardly anyone would even notice. . .