AI Chatbots Won’t Save Hollywood From the Writers’ Strike

AI Chatbots Won’t Save Hollywood From the Writers’ Strike

One of the less-than-gracious responses to the ongoing WGA strike is that writers could simply be replaced by scripts created by artificial intelligence (AI). There are many problems with this idea, one of which is the obvious: could a program like ChatGPT actually generate a decent sci-fi fantasy script?

We put the idea to the test, but it’s worth first noting that this scenario has real basis for concern. Predictive, generative writing programs, often referred to as AI, are a consideration for the Writers Guild of America and the exclusion of AI as a core writing software is included in the writers’ pattern of demands. The WGA wants to limit its use in writer’s rooms and make sure that any language generation models are used as a tool, rather than to create a final product, or even a developmental product. Another demand from the WGA is that AI will not be used to “rewrite” material. It also wants to guarantee that AI will not be trained on material written by guild members or covered under the minimum basic agreement (MBA). This last point might be the stickler, as public large language models, which are trained on a vast corpus of work, are not exactly forthcoming about what’s included in their library.

Even though ChatGPT — by far the most popular and recognisable generative text bot — is making huge jumps in development between its iterations (we’re currently on version four), it’s still a far cry from usable within the creative sector on its own. Or is it? Is ChatGPT, or any generative writing model, capable of replacing writers? Before we get into exactly what I did in an attempt to get ChatGPT to generate a script, let’s dive into the issues with AI generative models at a universal level.

How can you use ChatGPT?

First, a brief overview of how AI chatbots work. ChatGPT, for example, is what is commonly called a Large Language Model, because it is “trained” on a dataset (a corpus of work, texts, articles, etc.) and through mathematical formulas meant to imitate neural pathways, using an algorithmic average to produce the next word in a sentence. Using its artificial neural network, ChatGPT generates the next word that is most likely to appear based on previous words, but it does not know, or even have the ability to understand meaning — it only understands a word’s position as a datapoint within a sentence. ChatGPT has no intent whatsoever. To call this generation writing is a stretch of the imagination, as writing requires, at the very least, intention.

Currently there is also no way to copyright AI-generated text, another sticking point for people across the entire industry. Many involved in the writing process have brought this up as an issue with allowing AI writing into writers’ rooms. It seems that studio executives feel there might be a workaround somewhere — but there is no reassurance for writers that AI wouldn’t get credit or even be the sole credit on a piece, even if writers were forced to work from an AI-generated idea.

What are some of the problems with AI chatbots?

One of the problems I have with ChatGPT is that there are ethical concerns at nearly every level of its use and production. Not only are there issues with the library of text used to train the software, there are also ecological and labour problems at the core of the model’s use and development. According to Science Focus, the ChatGPT AI model “was trained using text databases from the internet.” The corpus includes data from books, Wikipedia, online articles, and “other pieces of writing on the internet. To be even more exact, 300 billion words were fed into the system.” To date, there has been no confirmation that OpenAI — the developers who programmed ChatGPT — have been given universal consent for these pieces of writing to be fed into their machine.

Another issue I had was that I assumed that by using ChatGPT I would be helping train ChatGPT. However, there is no indication that ChatGPT uses the text that it creates to “re-train” itself. It has a massive lexicon that is already slotted into its programming. Using ChatGPT does not make it better, as it cannot truly “understand” why you are asking it questions, correcting its output, or even “refining” the output. It is simply operating, not learning or developing a deeper understanding of the artificial neural pathways that have been coded into it. So that’s something, I suppose. Be reassured: ChatGPT does not eat itself. It does not think. It does not create. It just outputs. That’s a reassuring and frankly kind of gross way for anyone to imagine writing.

There are also ecological impacts for using the chatbot — it uses a lot of water to help cool down its servers, and, according to Gizmodo’s own reporting, “an average user’s conversational exchange with ChatGPT basically amounts to dumping a large bottle of fresh water out on the ground, according to a new study.” Not ideal. Additionally, Time recently discovered that OpenAI — the publishers of ChatGPT — took advantage of cheap labour in Kenya in the early stages of ChatGPT’s inception in order to keep costs down before they had funding secured. Another yikes. While a lot of the messaging around ChatGPT is centered around the elimination of labour, it’s clear that labour is an intrinsic part of training and keeping up the artificial neural network. Exploited workers programming the AI to create cohesive sentences, follow grammar rules, and even associate words with data input are are on the front lines of finding ways to develop a “smarter” AI.

While a core message around the use of ChatGPT and many other generative text models is that it will reduce the amount of work done by writers, Time’s reporting has made apparent that there is a huge amount of invisible labour being done behind the screens, often by underpaid or exploited workers. It is simply not ethical to use ChatGPT in any way, as its problems far outweigh its benefits, especially at this stage in its development.

How do you ask an AI chatbot produce a script?

Knowing all that, I’m still interested in seeing how it performs. While I am not looking to profit off any work that this test generates, I think it’s important to push its capabilities and see if it’s even at a level where it could potentially replace writers. My first entry: “I want to write a horror/fantasy story about demons possessing cars.” I’ve been on a horror kick recently, and Fast X is coming out soon. ChatGPT responded with a synopsis and then a breakdown of seven chapters and an epilogue. The synopsis read:

“In a quiet, unsuspecting town, a series of bizarre car accidents has left the residents bewildered and terrified. Little do they know, a sinister force is at play — a horde of demons has found a way to possess automobiles, turning innocent vehicles into instruments of malevolence. As the demonic presence grows stronger, a small group of courageous individuals must uncover the truth behind the possessed cars and find a way to stop the terror before the entire town is consumed by darkness.”

Less of a synopsis, more of a first draft of back-cover copy. This is the idea that someone has before they figure out what’s really happening in this story; it’s the idea before the idea is fully fleshed out. The chapter breakdown did follow basic narrative structures, but it was also… not all there. There were no real characteristics given to the main three characters (Emily, Natalie, and Marcus), there were no motivations, there was no depth. It was a shallow, empty husk of a story, the work of a model that understands the formula of storytelling but doesn’t quite know how to make it interesting, how to make it a story that means something beyond surface level plot progression.

I took the first chapter synopsis and asked ChatGPT to expand it. It’s a good enough opening shot; Emily is a mechanic working on her cars and she begins to hear the whisper of demonic forces in the engine she’s working on. The result was about 450 words that lacked style or even consideration. It was written from an omniscient point of view, something that has largely gone out of style in contemporary writing (one modern exception is Cat Rambo’s You Sexy Thing, a truly hilarious and wonderful sci-fi novel that deliberately engages with the POV). Close omniscient can lend itself very well to synopses — it’s a top-down view of literally everything going on in a scene, but it adds distance and removes the audience from the action if used incorrectly in the actual line by line writing. ChatGPT’s generation didn’t include a lot of emotion or presence either. It didn’t just lack style, it showcased a style vacuum. AI has an image of the language needed to develop a story, but no understanding of how to use it. It is a tool unable to use the tools that were used to build it.

Descriptions in the generated text are disembodied and removed from character. Some lines, as examples: “The atmosphere grows heavy with an unexplained sense of foreboding.” “A chill runs down Emily’s back, and her heart quickens its pace.” “As she draws closer, the whispers become clearer, weaving a chilling tale of dark desires and forgotten sins.” All of these are outlines of sentences, but they are not specific, they are not imminent. They require no context, they do not flow from one sentence to the next, they simply exist. It’s a poor way to write — but, you know what, we’re interested in a script. While this scene has Emily on her own, I ask ChatGPT to add in a phone call; “Let’s take the following scene and add dialogue. Have Emily chat with Marcus on speakerphone.” This was a chance for me to see if ChatGPT could take the established scene that shows an outline of something creepy, weird, and foreboding, and generate appropriate dialogue. I wasn’t going to hold my breath for characterization but maybe one or two lines would make sense.

Can ChatGPT write dialogue?

ChatGPT’s attempt at dialogue was laughably wooden and poorly constructed. Marcus answered Emily’s phone call and said that Emily sounded off before Emily even had a chance to speak. Emily and Marcus used each other’s names every time they spoke. Emily overexplained and spoke clearly, without any sense of fear or concern. She said “I can’t explain it, but I’m hearing whispers, whispers from an abandoned car. It’s unlike anything I’ve ever experienced before.” Like girl, no duh.

Moving past the sheer cringe of the writing, I decided that this was probably the best that ChatGPT could do without huge amounts of tweaking. Screenwriting has a lot of rules, some written, some unwritten, but it has a certain style to it, a cadence. I asked the model to turn this interaction into a script, and what it produced — while it did resemble something vaguely script-shaped — broke just about every rule in the book. It tried to output the exact same scene but reformatted the dialogue, keeping most of the phrasing the same. There was no cutting back and forth, no humour or horror, no movement within the scene, and very little tension. It wasn’t authorial or directorial, it was simply the shape of an idea. It was useless, even for a first draft. I didn’t push the model any further, deciding that I had enough to draw some conclusions.

Image: David McNew, Getty Images
Image: David McNew, Getty Images

Will AI tools replace writers?

In my opinion, no. Generative text-based AI is good for coming up with first-draft, back-cover copy. It has ideas for plots — but these are the kind of ideas that literally everyone who says “I’ve always wanted to write a screenplay” has kept in their wallets like old rewards cards. These kinds of ideas are not worth much. Besides the labour issues at play here (which present on multiple fronts) the truth is that Hollywood is full of ideas; ideas are cheap. Writing, however, is something very different, and something that takes skill, practice, and an intuition that AI simply can’t generate.

The best part of this experiment happened while I was analysing just how bad the generated text was, identifying the weak spots, and — spontaneously — understanding how the AI had failed, and brainstorming how I would have written it better. That might be a benefit of this tool — a way to figure out what not to do; a way to create something because the writer knows how writing works, and how people should act, how plots should be put together, and how to set a scene — and the AI is simply a machine for showing you the wrong way to do it.

The WGA is not unreasonable for seeking ways to limit this technology. You can read what ChatGPT came up with below. While none of what I produced was good, or even decent, it would not be outside of the scope of my imagination to think that an exec in Hollywood might think the first attempt at a story was “good enough” and give it to writers, expecting it to form the basis of a screenplay. Writers wouldn’t just have to rewrite the script, or the idea, they would have to come up with entirely new ideas. It wouldn’t be writing with AI, it would be writing over AI, writing better than AI, and ultimately writing without AI, as if it was never there, as if it hadn’t needed to be there at all.


Emily, a young mechanic, works diligently in her dimly lit garage. The clinking of tools and the occasional hum of an engine fill the air. Unbeknownst to her, an ominous presence lingers, casting its malevolent gaze upon her every move.

Emily painstakingly fine-tunes the engine of a vintage sports car. A sudden hush falls over the garage, and the atmosphere grows heavy with an unexplained sense of foreboding. The flickering lights cast eerie shadows on the walls, amplifying the feeling of unease.


(to herself)

Almost there… Just a little more…

Suddenly, a faint whisper, almost ethereal, carries through the air. It originates from an abandoned vehicle tucked away in the darkest corner of the garage. Emily’s ears strain to decipher the mysterious words, seemingly whispered from an otherworldly source. The voice is neither male nor female, but a haunting blend that sends shivers down her spine.


(furrowing her brows)

What was that?

A chill runs down Emily’s back, and her heart quickens its pace. She grabs her phone, her hands trembling, and dials Marcus, her best friend, on speakerphone.


(phone ringing)



(voice shaking)

Marcus, something strange is happening in the garage. I can’t explain it, but I’m hearing whispers, whispers from an abandoned car. It’s unlike anything I’ve ever experienced before.

There’s a brief pause on the other end of the line as Marcus processes Emily’s words.



Emily? Are you sure you’re ok? Maybe you’ve been working too hard lately. You know, long nights in the garage can play tricks on your mind.



I know it sounds crazy, Marcus, but these whispers are real. They’re growing louder and more insistent. They speak of dark desires and forgotten sins. I need you to believe me.

There’s a sense of hesitation in Marcus’s voice, but he recognises the sincerity in Emily’s plea.



Alright, Emily, I trust you. I’ll come over right away. We’ll figure this out together. Just promise me you’ll be careful until I get there.



Thank you, Marcus. I’ll be waiting.

Emily hangs up the phone, taking a deep breath. With Marcus on his way, she musters her courage and approaches the abandoned vehicle, determined to uncover the source of these haunting whispers and the secrets they hold within.

Little does Emily know that her encounter with the possessed car and its unearthly whispers is only the beginning of a nightmare that will soon consume her town, testing her strength, and unravelling the very fabric of her reality.


The Cheapest NBN 50 Plans

It’s the most popular NBN speed in Australia for a reason. Here are the cheapest plans available.

At Gizmodo, we independently select and write about stuff we love and think you'll like too. We have affiliate and advertising partnerships, which means we may collect a share of sales or other compensation from the links on this page. BTW – prices are accurate and items in stock at the time of posting.