“We shape our tools, and thereafter our tools shape us,” is a theory often ascribed to Marshall McLuhan, but was actually coined by Father John Culkin, a professor of communications at New York’s Fordham University, in 1967.

It is often used to suggest that the tools or technologies we create and use have a profound influence on the way we think, behave, and interact with the world. Essentially, the quote is saying that the tools we use shape our experiences and shape us as individuals. In other words, our tools and technologies shape our reality, and in turn, we are shaped by that reality.

A quick pause here to note that the above paragraph explaining Culkin’s theory wasn’t written by a human. It was generated by ChatGPT, the new artificial intelligence chatbot developed by San Francisco-based OpenAI (the company behind the image generation tool DALL.E 2), after it was asked to explain what the quote means.

ChatGPT launched as a prototype on Nov. 30, and has been quickly gaining traction and attention ever since, first from the tech industry, and more recently among the mainstream. It rocketed to more than one million users in just five days, and has led to handwringing and theorizing about its potential implications for society.

Its ability to uncannily replicate human speech and writing based on a simple prompts has been accompanied by not unexpected pronouncements about how it could radically transform industry X (and yes, both marketing and journalism—and presumably marketing journalism—are among them).

There are arguments that generative AI has “passed the tipping point,” that ChatGPT could completely upend academia by generating convincing student essays (OpenAI executives have said they plan to “watermark” its output) and it represents a “code red” for Google’s search business.

The implications of its capabilities could also extend into culture in myriad ways. Even through our own brief experimentation (including asking it to write a song about hate in the style of The Beatles, and a scene featuring Friends characters Joey, Ross and Rachel as mobsters) shows how it can be used to generate TV and movie scripts, write songs and, yes, presumably commercial scripts.

But are they good? That’s another question altogether. But it’s easy to see how any writer suffering a case of writer’s block would be intrigued. And in any case, this is just the first version; the experts who made the version we’re playing with now are bound to be working on one or two generational improvements down the road.

New technologies come and go all the time, of course, and many that have been fêted as breakthrough have been pilloried or fallen into obscurity, but ChatGPT—along with its sister image generation tool DALL•E 2—feels different.

This week, Bloomberg reported that Microsoft (which has a $1 billion investment in OpenAI) is planning to add ChatGPT to its Bing search engine, “betting that the more conversational and contextual replies to users’ queries will win over search users by supplying better-quality answers beyond links.”

For the moment, ChatGPT is being treated as more of a novelty. Not surprisingly, it has been enthusiastically adopted by the internet’s humour wing, with users asking it to write a biblical verse in the style of the King James Bible about how to remove a peanut butter sandwich from a VCR, or to write an excuse for not attending a meeting in the style of moody German director Werner Herzog.

But marketers are also taking notice. In Canada, for example, Unilever mayonnaise brand Hellmann’s recently invited a group of TikTok influencers to use ChatGPT to come up with a recipe using the leftovers in their refrigerator as part of its “Real Food is Too Good to Waste” positioning. Others are sure to follow.

Reuters reported last month that OpenAI expects to hit $1 billion in revenues by 2024, although at this point it’s not exactly clear what that path looks like. And in a Dec. 5 tweet, OpenAI CEO Sam Altman confirmed that the company plans to monetize the tool at some point. “The compute costs are eye-watering,” he said.

And, of course, there are also potentially troubling implications. The recent “Top Risks 2023″ report from Eurasia Group listed the rise of AI tools like ChatGPT among those risks, noting that they are capable of reliably passing the Turing test used to determine a machine’s ability to exhibit behaviour indistinguishable from that of a human.

The fact that AI has until now never been able to reliably mimic and/or replicate human speech has been a safeguard against the rise of our robotic overlords, but ChatGPT, even in its earliest incarnation, appears capable of shattering that illusion.

“These advances represent a step-change in AI’s potential to manipulate people and sow political chaos,” say the report authors. “When barriers to entry for creating content no longer exist, the volume of content rises exponentially, making it impossible for most citizens to reliably distinguish fact from fiction. Disinformation will flourish, and trust—the already-tenuous basis of social cohesion, commerce, and democracy—will erode further. This will remain the core currency of social media, which—by virtue of their private ownership, lack of regulation, and engagement-maximizing business model—are the ideal breeding ground for AI’s disruptive effects to go viral.”

Paul Kedrosky, a venture investor and internet analyst, even went so far as to label ChatGPT “a pocket nuclear bomb,” admonishing OpenAI for unleashing it without restrictions. “A virus has been released into the wild with no concern for the consequences,” he wrote.

Indeed, the implications for ChatGPT and other advanced AI to completely upend society and professional life seem profound. Marketing represents only a thin slice of the broader societal implications, but it’s what we do here at The Message, so we began contemplating its potential impact on our industry.

Yesterday, we ran a story written by ChatGPT about its potential to transform advertising copywriting. But as we worked on this story, we started to wonder if ChatGPT is more than just a transformative force. Could it be an existential threat to the many writers who earn a living in marketing?

So, we asked it. Here’s what it said:

“While it is possible for ChatGPT to generate human-like text, it is unlikely that it will be able to fully replace human copywriters. This is because ChatGPT lacks the creativity, empathy, and cultural knowledge that human copywriters bring to the table.

“Copywriting is more than just stringing words together; it is about understanding the target audience, crafting a message that will resonate with them, and effectively conveying the desired tone and brand voice. This requires a level of nuance and understanding that ChatGPT, or any other AI language model, is currently not capable of.

“Additionally, copywriting is often tied to specific marketing campaigns or branding efforts, which require a deep understanding of the company and its values. This is something that ChatGPT, or any other AI language model, cannot replicate.

“In short, while ChatGPT and other AI language models can be useful tools for generating text, they are unlikely to fully replace human copywriters in the foreseeable future.”

Do you feel more reassured by that response? Or less?