The Joy of Generative AI Cocreation
The Joy of Generative AI Cocreation
Don’t overthink AI. Act. Embrace it as a cocreator. Here’s how.
Years ago, a photography teacher gave me a project: take 100 pictures of the same object. It was an exercise in seeing. I chose a flowering bush in my backyard. The first ten shots were easy: I zoomed in, zoomed out, and tried a bunch of angles. Then, I was stuck.
90 more?
I stuck with it. I found new angles — wide and macro. I used my tripod to take shots from above, the side, and inside the bush. I played with aperture, shutter speed, and light. I cranked up the flash and blew out the exposure.
Most of my images were crap. Some were good. A few were cool.
But that wasn’t the point.
Every day, I meet people who are terrified, dismissive, or ignorant of AI. My first question to them is simple: "Have you tried it?" Mostly, the answer is no. Instead of debating why AI matters, I love to show them how it works. My mission is to help them understand that AI is a friend, not a foe.
AI is a tool. A coconspirator. A cocreator.
Like a camera.
When cameras were invented in the 1800s, painters revolted. They argued that photography wasn't art. Eventually, attitudes changed, and artists emerged, from Henri Cartier-Bresson to Richard Avedon to Diane Arbus to Annie Leibovitz, each armed with a unique point of view.
Working with AI is no different. (Well, it is, but more on that later). To illustrate this, I re-did my "100 shots" exercise with Midjourney. Again, I generated a bunch of junk.
But I also got some cool stuff. Here are nine of my favorites:
Was it “art” to create these images?
Some say no, just as some painters dismissed photography.
But, like my camera exercise, AI helped spark my creativity. It helped me generate over 400 images in a few hours. Each turn sparked an idea for a new prompt. I used my sense of what “good” looks like to choose my nine favorites above.
Is that art? I think so. Generative AI, to me, is like a camera — a powerful catalyst for creativity.
AI is More Than a Tool: It’s an Intern!
Generative AI is more complicated than a camera. It uses algorithms to transform your prompts into new, often surprising, output: words, images, code, music, videos, 3D images... There are hundreds of generative AI tools, and we're creating more every day.
That’s why Kevin Kelly, the founder of Wired Magazine, calls generative AI “the universal intern.” By placing AI on the level of an entry-level worker, he puts Jasper, Bard, ChatGPT, Jukedeck, and DALL-E in their rightful place.
That is, sometimes, generative AI generates good stuff; sometimes, it generates stinky stuff; always, it generates ideas different from your own, like an intern. Your job is to be the AI boss.
But I think generative AI is more than just an intern — it’s a fabulous, free, fantastic cocreator.
Generative AI —Your Crafty Cocreator
AI fears abound. The most common is about jobs. Yet Kelly boldly proclaims that not a single person will lose their job to AI. I think he’s right, with a twist.
I think lawyers who use AI will replace lawyers who don’t; marketers who use AI will replace marketers who don’t; salespeople who use AI will replace salespeople who don’t. AI is a crafty, essential cocreator. It makes humans better.
As with photography, the magic comes from the human. Without a human with a strong point of view, AI produces average, biased, crappy, and brilliant ideas indiscriminately. After all, they’re trained on the collective work of every human. On average, that’s average input.
Like photography, it’s hard work to create with AI. In Picture Limitless Creativity at Your Fingertips, Kelly writes, “The sobering secret of this new power is that the best applications of it are the result not of typing in a single prompt but of very long conversations between humans and machines. Progress comes from many iterations, back-and-forths, detours, and hours, sometimes days, of teamwork—all on the back of years of advancements in machine learning.”
If you discuss AI more than you use it, stop doing that. That’s what Kelly calls “thinkism.” Only action leads to learning, understanding, and progress.
So, like the exercise my photography professor gave me years ago, here are a few exercises to start engaging in the wonderful world of generative AI.
How to Become a Crafty Cocreator with AI
Pick a prompt, any prompt. Like “flower.”
Open your browser, visit Midjourney, and try some prompts. Start simple. Just type:
/imagine a flower in the style of <your favorite artist, vibe, or feel>
Creativity lies in your judgment and the choice of prompts, like the settings you choose on a camera and what you choose to point it at.
When I did this exercise with Midjourney, many of my results stunk. But some of the ones I shared above were pretty awesome and surprising. And, like my flower exercises, each attempt sparked new ideas to try.
Sometimes, I’d get stuck. I put the computer away, went about my day, and returned the next day. Creativity comes with space, time, and reflection.
I moved on from flowers to generate some art for this post. I wanted to convey AI as a partner. My first idea was to /imagine a writer writing with Yoda. But I decided against using him; I wanted something more “AI,” like a robot.
Next, I used AI to /imagine humans with robots. I did that for a while.
When I switched the prompt to “a robot in the style of Pixar,” I liked what I got!
A few days later, I noticed a print by the painter Joan Miró. I love his style, so I fired up Midjourney and tried: “/imagine a writer writing with a robot in the style of Miro.”
Although I loved what I got, I abandoned this path quickly — I couldn’t tell who the robot or the human was!
So I Googled for other famous artist prompts in Midjourney and started playing. This took me down an art rabbit hole. Eventually, I spotted another Midjourney user in its Discourse community use a prompt for David Hockney, which I tried with my prompt.
Here it is:
/imagine A writer hard at work with a partner robot, inspired by the painting of Nichols Canyon by David Hockney, abstract, unique, surprise --ar 16:9
This was my favorite style, so I kept trying variations of it and settled on the cover photo for this article above. This was one I did not use; I liked the one where the robot was looking at the human, almost with empathy.
Infinite Mediums, Infinite Questions, Infinite Creative Opportunities
You can repeat this exercise with any generative AI tool. For example, if you’re writing, try ChatGPT. Choose a subject and try some of these prompts:
Summarize what <your audience> needs to know about <subject>1
Write a 6-word-story for <your writing>2
Write five headline ideas for <your article>3
Find five credible sources for <your topic>
Summarize <your writing>
Write a funny summary of <your article>4
Improve <your writing> for clarity.
Improve <your writing> for flaws in logic5
You can spend hours with prompts like this. Each may lead you down a new creative path, like a new camera aperture or shutter speed setting.
Is that art? I think so.
There is No “Think,” Only “Do”
As Yoda might say, "Mmm, what's of this AI, hmm? Like my photography teacher's assignment, taking 100 pictures of a flower, it is. Daunting at first, it may seem. Creativity and inspiration, terrible and awesome results, you shall get. Who knows, jokes that are actually funny, you might generate!"
ENDNOTES
Generative AI can be a great way to spark writing ideas. I didn’t use it for this article, but I could have, based on this answer to my prompt: “Summarize what you need to know about working with Generative AI, like Midjourney”:
Generative AI tools like Midjourney can be a powerful way to spark creativity and generate new ideas. While these tools may produce some mistakes and require guidance, they can be useful co-creator to assist in the creative process. It is essential to understand that AI should not be seen as a foe but rather as a complementary tool that requires users to experiment and iterate to achieve the best results. Individuals can benefit from the infinite creative possibilities of generative AI tools by using prompts and allowing for space and time for reflection.
That’s good! But I think my article is better :)
I gave this prompt in ChatGPT and pasted the entire article text you just read: “Write a 6-word story for <this article>. It responded:
"Act. Embrace generative AI. Thrive together."
Not bad!
So I played with that idea. I liked its choice of “act” and “embrace.” After a dozen or so iterations, I landed on:
Don’t overthink AI. Act. Embrace it as a cocreator. Here’s how.
Here are some of the options ChatGPT gave me for headlines for this article:
"Unleash Your Creativity: Harness Generative AI for Art and Innovation"
"Supercharge Your Writing: Let AI Assist Your Article Summaries"
"Expand Your Knowledge: Discover New Sources with Generative AI"
"The Power of Generative AI: Summarizing Patents Made Easy"
"Master the Art of Problem-Solving with AI: Unlock New Possibilities"
I didn’t love any of these but had various drafts of headlines for a few weeks. Finally, on a bike ride, listening to this podcast interview of Kevin Kelly with Tim Ferriss, it struck me how joyful Kelly is about AI and its use. He spoke of pulling all-nighters with Midjourney to create the perfect image.
I decided that the feeling of joy is what I wanted to put in my headline, and used my iPhone journaling app, Day One, to capture this idea for the headline of my article: “The Joy of Generative AI.”
I got home, tweaked that article title a bit, and landed on the one I used: The Joy of Generative AI Cocreation
First, I got this:
“Don't overthink AI – act and embrace it as a co-creator. And who knows? You might find joy, just like Kevin Kelly pulling all-nighters with Midjourney to create the perfect image.”
Not too funny! So I tried “Write a joke about this article in the style of Jerry Seinfeld.” After several attempts, I liked how it started with “What’s the deal with AI?” That sounds like Seinfeld.
I also liked one line that sounded like a punchline: “Who knows, you might even generate some jokes that are funny!”
So, I put those two elements together with a summary to get this:
What's the deal with AI? It's like my photography teacher's assignment to take 100 pictures of a flower. At first, it’s daunting. But with creativity and experimentation, you’ll get surprising and awesome results. Who knows, you might even generate some jokes that are funny!
Then, I changed my mind. I went with Yoda instead. See the conclusion above ^^^
When I asked Jasper to find a logic flaw in this article, here’s what it said approximately:
The logical flaw in this article is the statement that Kevin Kelly boldly proclaims that not a single person will lose their job to AI. This is an overgeneralization and not a fact. While it is true that AI can create new job opportunities, it can also lead to the displacement of some jobs. The impact of AI on employment is a complex issue and cannot be reduced to a simple statement. It is essential to carefully consider the potential consequences and benefits of AI in the workplace.
I loved that. Indeed, Kelly’s statement is surprising and an over-generalization. And that’s what makes it very human and fun to write about. So, screw you, Jasper.ai; I’m keeping it in there and look forward to debating other humans about this spikey point of view.
Here's an article from Thabata Romanowski about a data + analog art project -- she started with DATA about her world and created ANALOG art from it.
I found it fascinating to read in the context of "what would be the role of AI in her process?" and thought I'd share it here. It's a great read:
https://nightingaledvs.com/data-art-self-portrait
(Going to try my best not to turn this comment into its own post lol)
Thank you Mark for opening this up for discussion, and doing so in such a welcoming way. Enjoyed reading this piece.
First and foremost, the images that generative AI is capable of can be truly stunning. No arguments there. The ease with which these images can now be generated is equally stunning. No argument there either.
Does this empower more people with more ways to produce artistic images? Absolutely. Does this bestow artistic genius on people who've never picked up a paintbrush? Absolutely not.
You ask "Was it 'art' to create these images?" The images themselves are art, yes. It's not human-made art, it's machine-generated art with input or creative direction from a human. If we must anthropomorphize, the AI is the artist and the human typing in the prompts is the client (not necessarily the creative director, you'd still need some professional cred for that)
I was intrigued by this paragraph: "If you discuss AI more than you use it, stop doing that. That’s what Kelly calls 'thinkism.' Only action leads to learning, understanding, and progress." So, for full transparency, I've used both generative image and text AI in my research. After all, I can't write about something I haven't actually used and worked with, to your point Mark. But because design, photography, and writing are in my professional wheelhouse (I'm a working author, amateur photographer, and I used to run a small design firm), I became pretty disenchanted pretty quickly—not so much bc of the quality (some of that yes) but more bc of the EXPERIENCE.
Here's the problem. Generative AI takes all the joy and challenge out of the process, the journey of artistic creation. No way in hell will I let ChatGPT write my posts or novels, because a) it's not me; b) I hate babysiting; and c) I enjoy, very much, the work of writing. So become the nanny of a robot writer I shall not :) Nor to feed the LLMs with my future writing do I wish.
This is not to say others should never use it. I can see plenty of use cases where gen AI is quite helpful and valuable.
Re: the painters revolt against the big bad camera and the new art of photography. The same can of course be said about digital tools like Photoshop or Painter. The difference with generative image AI systems is that they were trained on artists' work, without their knowledge, without their permission, and without compensation. The camera is a piece of mechanical equipment (yes now with software)—not trained on artists' work. Digital tools are software also not trained on artists' work. This is where many artists and writers and other creators feel the betrayal has taken place—it is not the algorithm itself but the way in which the developers chose, consciously, to train it. They could have contacted the artists and photographers beforehand. You know, worked with them, asked for permission. Would they have been able to assemble training data sets as large as the ones they've got? Probably not. This is where these thorny ethical questions lie. This many people feeling this passionately about a technology can't be wrong—and they're not wrong. This is their passion, their right, their livelihood in many ways.
One more thing and I'll hop off the pedestal. At the end of the day, we need to ask ourselves, how much of our creative agency and our own intellect do we want to farm out to LLMs, and at what price? It's an open-ended question.
(p.s. Ray you can stop with the pills now really)