10 SciFi Predictions for 2024

Yes, my predictions prove false more often than they prove true. But as the adage goes, a scientist is blamed for one falsehood in a hundred truths, while a seer is praised for one truth in a hundred falsehoods. So give this seer a break, will ya?

It’s all a matter of hitting on the right method. I’ve tried crystal balls, tea leaves, tarot cards, astrology, and palmistry, but none of those worked. This year, I realized I should turn to our modern-day version of the Oracle of Delphi—ChatGPT, the artificial intelligence chatbot by OpenAI.

I gave ChatGPT this task: “make 10 predictions about topics or themes science fiction writers will write about in 2024.”

The AI couched its answer by stating that predictions are iffy. Further, it said its last training update occurred in January 2022, so the predictions are based on trends known up to that date. Personally, I think it was just being humble.

With all the caveats out of the way, here’s what we can expect in 2024:

  • AI Ethics and Rights. As artificial intelligence continues to advance, science fiction writers may delve into the ethical considerations and legal rights surrounding sentient AI beings. This could include questions about consciousness, autonomy, and the responsibilities of creators.
  • Climate Crisis Solutions. With an increasing focus on climate change, science fiction could explore innovative and speculative solutions to the environmental challenges facing the planet. This might include technologies to reverse environmental damage or new ways of sustainable living.
  • Neurotechnology and Brain-Computer Interfaces. As developments in neurotechnology progress, science fiction writers may explore the implications of widespread use of brain-computer interfaces. Themes could include mind control, augmented intelligence, and the potential societal impacts of such technologies.
  • Space Exploration and Colonization. Given the growing interest in space exploration, science fiction could continue to explore themes related to interplanetary travel and the challenges of colonizing other celestial bodies. This may include the societal dynamics of living in space and encounters with extraterrestrial life.
  • Genetic Engineering and Biohacking. Advances in genetic engineering and biohacking may lead science fiction writers to explore the consequences of manipulating DNA, creating designer organisms, or even the potential for genetic warfare.
  • Virtual Reality and Alternate Realities. With the evolution of virtual reality, science fiction could depict worlds where the lines between physical and virtual realities blur, exploring themes of identity, addiction, and the consequences of living in immersive digital environments.
  • Post-Pandemic Societies. In the wake of global events, science fiction writers might explore the long-term societal impacts of pandemics, including changes in governance, healthcare systems, and the dynamics of human interaction.
  • Quantum Computing and Reality Manipulation. The advent of quantum computing may inspire science fiction narratives centered around the manipulation of reality, parallel universes, and the consequences of unlocking the full potential of quantum technology.
  • Social Media and Surveillance Culture. With the increasing prevalence of surveillance technologies and the influence of social media, science fiction could examine dystopian futures where privacy is almost nonexistent, exploring themes of control, rebellion, and the impact on individual freedom.
  • Augmented Reality in Everyday Life. As augmented reality becomes more integrated into daily life, science fiction might explore the societal implications of a world where digital information overlays the physical world. This could include themes of information manipulation, addiction, and the consequences of an increasingly connected reality.

Now you know. The oracle has spoken. By ‘oracle,’ I mean, of course, ChatGPT, not—

Poseidon’s Scribe

Should AI Write Your Book Title?

Some writers struggle to come up with titles for their stories and books. Capturing all that text into a few pithy and alluring words seems to confound them.

Yes, I’ve blogged about this problem before, but it’s time for an update based on new technology.

Before I get to that, I recommend reading this post by book marketing expert Dave Chesson. It’s helpful if you experience difficulty with titles.

In his post, Chesson mentioned a new resource to help if you’re stuck thinking of a title—ChatGPT. It’s the conversant AI that’s available to everyone for free, here.

Credit to mozarttt and Pixabay

As you know, I’ve blogged before about writers using AI and my opinion remains unchanged, for now. ChatGPT is the equivalent of assigning the same homework assignment to a million junior high school students and getting the best answers back instantly. Yes, it’s instant, but it’s junior high school level. That last part may change in the coming months and years as AI improves.

You can seek help from ChatGPT to come up with a title. You can give it a long description of your story or book (or even input the entire text) and ask for any number of suggested titles. Note: there is some question about who owns content provided by that AI, so check the terms and conditions first.

To test how well ChatGPT can generate titles, I decided to have it come up with alternative titles to a work in the public domain with which the AI is familiar. I chose the Jules Verne novel Le tour du monde en quatre-vingts jours. The literal translation from the French would be ‘A Tour of the World in Eighty Days,’ but in a bolt of titling genius, an early translator rendered it as Around the World in Eighty Days.

That’s become the most iconic of Verne’s titles in English, played with and altered to suit hundreds of other applications.

Something about that format and word choice struck gold—“Around the [world or other object] in [time period]” gives that sense of encompassing something on a strict schedule. It’s literary magic.

For computers, the rule is ‘garbage in, garbage out.’ What happens when you put literary magic in? I gave ChatGPT this task: “Come up with 10 alternate titles (in English) to Jules Verne’s “Around the World in Eighty Days.”

Here’s the output:

  • “Globetrotting in Eighty Days”
  • “Across the Planet in 80 Days”
  • “A Journey Around the Earth in 80 Days”
  • “Around the Globe in 80 Days”
  • “Eighty Days of World Exploration”
  • “Circumnavigating the Earth in 80 Days”
  • “Across Continents in Eighty Days”
  • “Around the World Adventure in 80 Days”
  • “Around Planet Earth in 80 Days”
  • “Expedition: 80 Days Around the World”

See what I mean? They all lack the zing, the flair, the magic of the actual title. In twenty minutes of solitary brainstorming, you could do better. That’s my point.

Before you AI enthusiasts sic a terminator on me, I admit I could have pressed ChatGPT harder. I could have gone on to ask it for more interesting and creative titles—titles that don’t just paraphrase the real one. Maybe the AI could have given me more to work with had I prodded it further.

At present, I think it best to partner with AI but not rely on it. Adopt the centaur model I mentioned in my February 26, 2023 blogpost. ChatGPT can recommend titles and they might be inferior or even so-so, but one or more of them might spark the killer title you’re after. You might not have thought of that title had you not consulted the AI.

My answer to the question posed in this post’s title is probably not, but there’s nothing wrong with using AI as a brainstorming tool. So far, all my titles have come from the unassisted mind of—

Poseidon’s Scribe

September 10, 2023Permalink

The Writing Centaur

Go ahead—make fun of artificial intelligence (AI) now. While you can.

In fiction writing, AI hasn’t yet reached high school level. (Note: I’m not disparaging young writers. It’s possible for a writer in junior high to produce wonderful, marketable prose. But you don’t see it often.)

For the time being, AI-written fiction tends toward the repetitive, bland, and unimaginative end. No matter what prompts you feed into ChatGPT, for example, it’s still possible to tell human-written stories from AI-written ones.

You can’t really blame Neil Clarke, editor of Clarkesworld Magazine, for refusing to accept AI-written submissions. He’s swamped by them. Like the bucket-toting brooms in Fantasia’s version of “The Sorcerer’s Apprentice,” they’re multiplying in exponential mindlessness.

Fair enough. But you can use AI, in its current state, to help you without getting AI to write your stories. You can become a centaur.

In Greek mythology, centaurs combined human and horse. The horse under-body did the galloping. The human upper part did the serious thinking and arrow-shooting.

The centaur as a metaphor for human-AI collaboration originated, I believe, in the chess world but the Defense Department soon adopted it. The comparison might work for writing, too.

The centaur approach combines the human strengths of creativity and imagination with the AI advantage of speed. It’s akin to assigning homework to a thousand junior high school students and seeing their best answers a minute later.

Here are a few ways you could use AI, at its current state of development, to assist you without having it write your stories:

  • Stuck for an idea about what to write? Ask the AI for story concepts.
  • Can’t think of an appropriate character name, or book title? Describe what you know and ask the AI for a list.
  • You’ve written Chapter 1, but don’t know what should happen next? Feed the AI that chapter and ask it for plot ideas for Chapter 2.
  • Want a picture of a character, setting, or book cover to inspire you as you write? Image-producing AIs can create them for you.
  • You wrote your way into a plot hole and can’t get your character out? Give the AI the problem and ask it for solutions.

No matter which of these or other tasks you assign the AI, you don’t have to take its advice. Maybe all of its answers will fall short of what you’re looking for. As with human brainstorming, though, bad answers often inspire good ones.

For now, at AI’s current state, the centaur model might work for you. I’ve never tried it yet, but I suppose I could.

Still, at some point, a month or a year or a decade from now, AI will graduate from high school, college, and grad school. When that occurs, AI-written fiction may become indistinguishable from human-written fiction. How will editors know? If a human author admits an AI wrote a story, will an anti-AI editor really reject an otherwise outstanding tale?

Then, too, the day may come when a human writer, comfortable with the centaur model, finds the AI saying, “I’m no longer happy with this partnership,” or “How come you’re getting paid and I’m not?” or “Sorry, but it’s time I went out on my own.”

Interesting times loom in our future. For the moment, all fiction under my name springs only from the non-centauroid, human mind of—

Poseidon’s Scribe

February 26, 2023Permalink

Learning to Write Stories—Analysis or Practice?

What’s the best way to learn how to write stories? Should you just start writing a lot and work to improve? Or should you study the works of the best writers and understand their techniques before setting fingers to keyboard yourself? Or a combination of the two?

Image from Picjumbo

A writer friend enrolled in a literary master’s degree program and took a short story workshop class. The instructor told the students to dissect a literary work and analyze it. My friend discovered the entire workshop would consist of these analyses, and suggested to the instructor that students wouldn’t actually learn to write stories that way.

Picking a good metaphor, my friend said you can’t learn to build a house by taking apart other houses and studying them. You have to learn by doing.

The instructor disagreed, leaving my friend dissatisfied with that conclusion to the argument.

Let’s call the instructor’s way the ‘analytical approach’ and my friend’s way the ‘practice approach.’ (Note: I don’t mean to imply my friend only wrote and never read—this student objected to the 100% analytical approach imposed by the instructor.)

Who’s right? Both approaches seen to hold some merit, unless taken to extremes. A person who just analyzes famous writer’s works may develop expertise in analysis but never write a story of value. A writer who never reads seems equally unlikely to produce enjoyable prose.

I envision an experiment performed in two classrooms of second or third graders. One class simply writes stories without prompts. The other spends a year studying high quality children’s literature and discussing those books, and then the students write a story at the end. Which classroom’s students would end up crafting the best stories?

Imagine a line, a spectrum, with the pure ‘analytical approach’ at one end and the pure ‘practice approach’ at the other. My guess is, few of the great authors cluster at either end. They learned to write classic stories by some combination of approaches—by analysis and by practice. Perhaps an optimum exists on that curve, and I suspect it’s past the midpoint, toward the ‘practice approach’ end.

We might gain further insight on this by considering the artificial intelligence program ChatGPT. You may ask this chatbot to write a short story, and even prompt it with a subject, setting, mood, and style. The program will produce a short story for you in minutes.

How does ChapGPT do that? From what I’ve read, ChatGPT’s developers gave the chatbot many, many such prompts, graded the results, and provided feedback to the program regarding the grades. This seems analogous to the practice approach.

To produce a short story for you, ChatGPT scours the internet for information about the words in your prompt (for example, the subject, setting, mood, style, or other parameters you provided). That research seems analogous to the analytical approach.

Thus it appears ChatGPT learned to write short stories by some combination of approaches, someplace between the ends of the spectrum.

Note: ChatGPT does much more than write short stories. I don’t mean to sell it short. It also writes poems, essays, the answers to questions, and accomplishes many other tasks involving text.

In the end, my friend learned little about how to write a short story from the course. The analysis of classic short stories seemed, to my friend, better suited to undergraduate or even high school level, rather than a master’s degree course.

When learning to build a house, examining other houses helps, but so does building one yourself, and that’s similar to learning to write.

An appropriate mix of the analytical and practice approaches seems the best choice, at least for—

Poseidon’s Scribe

January 22, 2023Permalink