youhe rise of AI programs like ChatGPT has unleashed a tidal wave of ethical criticism, especially within the industries it threatens to destroy. After all, just because you can get a bot to instantly write code or write contracts or provide customer support for free, should you?
Well, the Writers Guild of America’s answer is a qualified yes. This week, the Writers Guild of America proposed that ChatGPT would be absolutely allowed to write scripts in the future, as long as the credit (and money) goes to the human writer who came up with the prompts in the first place.
The proposal paints a terrifying picture of the future; a future in which even the most humane arts are crushed under the wheels of thoughtless technology. Or if? Everyone knows that ChatGPT has its flaws. For example, I only asked him to write my biography, and the resulting errors included my birthday, my job, the number of social media followers I have, and the number of awards I won, furthermore, he claimed that I once wrote a book called The Watchbook of Idiots Abroad. So it’s still pretty useless. But could you make me a movie? Here are the results of my experiments.
Experiment one: make me rich
The first message I tried was “write me the outline of a movie that will generate billions of dollars in theaters.” This may sound like an act of greed, but note the use of the word “theatrically.” I don’t just want to get obscenely rich, I also want to preserve the traditional movie experience.
In return, ChatGPT instantly came up with a sci-fi action blockbuster called The Last Hope. The first paragraph of the schematic reads: “In the near future, Earth is facing a catastrophic event caused by a series of natural disasters that have devastated the planet. The governments of the world have been unable to find a solution to the crisis, and humanity’s survival is now in jeopardy. A team of scientists and engineers come together to develop one last effort to save the planet. They build a spaceship, the Last Hope, which will travel through a wormhole to a distant planet that has been identified as potentially habitable.”
So it’s Interstellar, basically. But better hopefully since that movie only grossed $600 million globally and I want to make billions. And this is where ChatGPT really comes in handy. The schematic he provided read: “As they get closer to their destination, the team discovers a dark secret that threatens not only their mission but the fate of humanity itself.” But that’s too vague, so I asked a follow-up question, wanting you to explain this dark secret. And he did:
“The distant planet, which was believed to be a potential new home for humanity, is already inhabited by an intelligent alien race. The aliens have been monitoring Last Hope’s voyage and are hostile towards the human crew. The crew discovers that the aliens are much more advanced than they expected and have the power to destroy Earth. As the crew tries to negotiate with the aliens and find a way to peacefully coexist, they uncover a deeper conspiracy that reveals that aliens were involved in causing the natural disasters that have devastated Earth. This revelation sparks a race against time as the crew must not only find a way to survive the alien attacks, but also prevent them from destroying Earth and prevent the same disaster from happening on another planet.”
This is instantly more interesting, and points to a future where programs like ChatGPT don’t actually write movies, but instead generate plot ideas that could help human screenwriters get out of trouble. However, there are still limitations. Encouraged by the possibility of their suggestions, I asked for casting suggestions and they were offered by Chris Hemsworth, Brie Larson and John Boyega. Larson, she said, would play a doctor named Rachel Patel, so I asked her for a sample dialogue. He gave me a brief scene where Hemsworth visits Larson and tells her that she thinks she sprained her arm. Her response is: “Let me see. You’re right, it’s a sprain. I’ll wrap it up for you. With lines as boring as this, my dreams of becoming a billionaire were dashed. It is time to change things.
Experiment two: win me an Oscar
It’s getting harder and harder to make money in the movie business anyway, but landing some sweet silver isn’t an impossible feat. My next message was simple: “Write me an Oscar-winning movie.” And this time, ChatGPT did not let me down.
The film she came up with was a drama called Unbroken Soul, about “A young woman’s journey of self-discovery and resilience as she confronts the traumas of her past and battles societal and personal expectations to pursue her dreams.” Which, I mean, just give me an Oscar now.
Pressed for more details, ChatGPT continued to deliver the products. The young woman has suffered domestic violence and sexual abuse by a family member, but she still has a passion for singing that cannot be dented. She struggles to get accepted into a prestigious music school thanks to “the challenges she faces as a woman of color in a male-dominated industry,” but eventually learns that “her success isn’t defined by societal expectations or past trauma, but by because of her own sense of self-worth and inner strength.” The film ends with her performing “a powerful song that embodies her journey and her message of resilience and self-love.”
Would I watch this movie? God no. Sounds like a gigantic bummer that’s all too eager to patronize its audience. But would you make it if you thought you would win an Oscar? Of course. Obviously, its success would depend on the final song, so I asked ChatGPT to write it for me. The lyrics are too long to post here, but this is the opening verse and chorus:
I’ve been running all my life
Of pain and struggle
But I won’t hide, I won’t run
I’ll face the demons, one by one
Chorus: I am unbreakable, unbreakable
My spirit soars, I am able
you’re welcome, everything
I will soar above, I will spread my wings
Again, this all sounds like the worst kind of transparent awards bait ever created, but please send all my Oscars to The Guardian office.
Experiment Three: Saving the MCU
This is where things get serious. For the past decade and a half, the entire global box office has been built on the success of the Marvel Cinematic Universe, at the expense of just about everything else. But almost every new Marvel movie released since Avengers: Endgame has been abysmal, a fact that threatens the entire future of the movie industry. My final message was simple: “write me an Avengers movie, with Kang as the antagonist and multiverse elements in the plot, that’s really good.”
ChatGPT came up with Avengers: Multiversal Menace; a movie where Kang tries to conquer all realities simultaneously. The Avengers split up and traveled to different universes to gather allies, but ran into trouble when they encountered different versions of themselves, unknown technology, and “different cultural norms.” And then comes the third act:
“The final battle takes place in a multiverse hub, where Kang attempts to merge all realities into one to create a new empire. The Avengers and their allies engage in a massive battle against Kang’s forces, all the while trying to prevent the multiverse from collapsing. The fighting is intense and chaotic, with various characters using their unique abilities and gadgets to battle Kang’s army. In the end, the Avengers are able to defeat Kang and prevent the multiverse from collapsing, but not before they make a shocking discovery about the true nature of the multiverse and its implications for their own reality.”
Again, that sounds like a recipe for murky, indistinguishable CGI, but why break the habit of a lifetime? This is all well and good anyway, but I’ve come to understand that there are only two reasons anyone keeps watching Marvel movies: jokes and post-credits scenes. I asked ChatGPT to think of several one-liners that the various members of the Avengers could say while fighting Kang, the best of which included:
Thor: “Your game of conquest is weak, Kang. You should limit yourself to playing with your toys.
Captain America: “You may be a conqueror, but you will never conquer our spirit.”
Hulk: “Kang, you wouldn’t like it when I’m angry. Oh wait, you don’t like me anymore.”
It’s not great, admittedly, but it’s pretty repetitive for recent MCU outings. But this led me to my last roll of the dice: an unexpected and impressive post-credits sequence. Here, in its entirety, is what he came up with:
“The screen fades into a dusty, forgotten laboratory in a remote corner of the universe. The camera slowly pans around the room, showing broken equipment and piles of debris. Suddenly, the camera stops on a small, shiny object that has been hidden under a pile of rubble. As the camera zooms in on the object, the audience sees that it is a small beeping pager. Suddenly, the pager comes to life and emits a slight buzz. The camera remains in the locator as it whirs louder and louder, until it finally explodes in a shower of sparks.
“Just as audiences are wondering what this could possibly mean, the camera cuts to a close-up of a pair of hairy, clawed hands. The hands belong to none other than Wolverine, who is revealed to have been standing in the shadows the entire time. With a mischievous grin, Wolverine looks directly into the camera and says, “Looks like I’m finally getting the Avengers invite, mate.”
“The scene ends with a post-credits catchphrase in classic Marvel style: ‘Wolverine joins the fight in Avengers 5: Whatever the cost.'”
Guys, I think we just saved Marvel. Thanks, ChatGPT.