Will ChatGPT replace the marcomms department? ‘No’
Vice president of marketing and communications at Akkodis Australia, Lisa Collins, takes a closer look at ChatGPT to see if she, like many comms and marketing professionals, is about to be replaced by AI.
I began this article by spending several hours reading various online news articles, talking with colleagues, friends, and academics, and then jotting down some notes for further development.
When I sat down to review and expand on my notes, I asked ChatGPT:
“Respond to a journalist about the applications, considerations and challenges of using ChatGTP for marketing.”
In a matter of seconds, I received the following response:
ChatGPT can be used for a variety of marketing applications, including creating engaging content, answering frequently asked questions, and personalising customer interactions. However, there are also considerations and challenges to keep in mind when using ChatGPT for marketing.
One consideration is the potential for bias in the model’s responses, as it is trained on a dataset that may contain biases. It’s important to monitor the output and fine-tune the model to mitigate any biases.
Another consideration is the need for a high-quality training dataset to ensure the model’s responses are accurate and relevant. This can be a significant challenge, as it requires a large amount of diverse and well-labeled data.
Additionally, there may be regulatory and ethical concerns around the use of ChatGPT in marketing, such as ensuring customer consent and transparency in the use of the model.
In summary, ChatGPT has the potential to greatly enhance marketing efforts, but it’s important to be aware of the considerations and challenges that come with using the model.
I was relieved. While ChatGPT confirmed some of the functional applications I had identified – creating engaging content, answering frequently asked questions, and personalising customer interactions – the considerations are generic at best. What gives me some comfort is I believe I can provide some human insights on the impact of this new technology.
There has always been an ethical and moral dilemma around the implementation of new technology. For example, the Luddites in 19th century Britain smashed the new weaving looms, fearing the new technology would be devastating to their craft; when automobiles took over from the horse and cart there were societal concerns about safety, pollution, and the impact on rural life… and so on to this day.
Remembering the Luddites from my year-12 Modern History class, I asked ChatGPT: “What were the concerns of the Luddites?”
*The following content was generated by ChatGPT
The Luddites were a group of 19th century English textile workers and weavers who opposed the use of new machinery in the textile industry. They believed that the new machines were taking away their jobs, lowering wages, and threatening their traditional way of life. Some of the concerns of the Luddites were:
1. Job Loss: The Luddites were primarily concerned about the loss of their jobs due to the increased use of machinery in the textile industry. They believed that the machines would replace skilled human labor, and lead to widespread unemployment.
2. Lower Wages: The Luddites also believed that the use of machinery would lead to lower wages for those who were able to keep their jobs. They feared that factory owners would be able to pay workers less, as they wouldn’t need to pay as many people to operate the machines.
3. Threat to Traditional Skills: The Luddites also believed that the new machines would make traditional textile skills obsolete. They feared that their children would not be able to learn the same skills and craftsmanship that they had.
4. Social Disruption: The Luddites also believed that the new machinery would lead to social disruption, as workers would be forced to move from rural areas to the cities to find work. They believed that this would lead to the erosion of traditional communities and ways of life.
5. Negative Impact on Quality: The Luddites also believed that the new machines would produce goods of lower quality than those made by hand. They argued that the new machines would produce goods quickly and cheaply, but the quality would be poor.
Overall, the Luddites were concerned about the impact of new technology on their jobs, wages, traditional skills, communities, and quality of goods. They believed that the new machines would have a negative impact on their lives and livelihoods.
*End ChatGPT response
When it comes to ChatGPT, the concerns of the Luddites are broadly applicable to modern marketers and media professionals: job losses, lower wages, threat to traditional skills, social disruption and negative impact on quality are all potential impacts of this new platform.
Reading an article written by Emma Whiten, Marketing News Canada, she voices some concerns familiar to the Luddites:
“Despite the many benefits and usable features of this tool, many marketing professionals (me included) are wondering how this will impact the world of marketing. As the popularity of these tools grows, the threat of automation and job redundancy is on the minds of many Canadian marketing professionals. Freelancers especially are now having to compete with AI technologies that can afford to be priced well below the market value.”
Last week Vanity Fair published an article titled ‘ChatGPT’S mind-boggling, possibly dystopian impact on the media world’.
“ChatGPT can get stuff out much faster and, frankly, in a much more articulate way. A lot of the Russian disinformation in 2016 wasn’t very good. The grammar and spelling was bad. This looks really smooth.” https://t.co/5On0ecTcpl
— Joe Pompeo (@joepompeo) January 27, 2023
In the article, Joe Pompeo asked:
‘Is artificial intelligence “useful for journalism” or a “misinformation superspreader”? With CNET mired in controversy, Jonah Peretti (BuzzFeed CEO) promising “endless opportunities,” and Steven Brill (veteran newsman and media entrepreneur) warning of AI’s weaponisation, the industry is only just coming to grips with this jaw-dropping technology.’
Some familiar refrains could be found in the article: concerns about quality, misinformation, accuracy, and ethics. All valid, and all questions that will need to be addressed by humans.
As with all technologies, the ethical application of these tools is imperative and difficult to enforce. Regulation across the sector is still playing catch-up, with the application of AI and ML of particular concern to ethicists and legislators.
The use of AI powered tools in marketing is not new. Chatbots, automated customer service processing and AI writing tools have become ubiquitous across the sector. What makes ChatGPT a game-changer is the scope of data available in its responses. It is one of the largest and most powerful language processing AI models to date, with 175 billion parameters.
It is important to remember that even the most sophisticated machine learning models and artificial intelligence programs are retrospective. They can only process existing information. They are Proustian in that the process is akin to “Remembrance of Things Past.’ ChatGPT (at least at this stage) is not generating new ideas.
As I work in technology marketing, I have been involved in communicating the business benefits of many applied technologies. When thinking about the potential benefits of ChatGPT I was reminded of some of the principles of cloud economics.
Amazon Web Services (AWS) developed a Cloud Value Framework (CVF) based on four pillars – or as AWS calls them “key dimensions of value:” cost savings, staff productivity, operational resilience, and business agility.
At a high-level, the benefits of applying ChatGPT to marketing are similar. Particularly when it comes to staff productivity. In cloud economics, there is an augment for redeploying highly skilled IT resources formerly engaged with maintaining servers – AKA ‘keeping the lights on’ – to higher-value tasks that create business value.
Similarly, marketing professionals can save time by automating lower-value repetitive tasks like research, blog outlines, responding to customer service and social media questions etc., freeing up valuable human resources to do what humans do best – think creatively.
Likewise, at least at this stage, human intervention is required to address the very real concerns about accuracy and ethics. As described in various articles, AI is not 100% accurate: the fact checking, clarification, protections of privacy and resolution of ethical considerations provided by human intervention are perhaps where the true value lies.
Finally, to derive real value from a tool like ChatGPT, the user must frame the hypothesis in such a way that the response provided is useful. Framing the problem to be solved, asking the right questions, and assembling and fact checking the responses are the human nuances that will drive the creative use of this platform. If marketers can gain efficiency through technology in the pursuit of engaging, informative and relevant marketing activities, then so be it.
I will close with another quote from the Vanity Fair article:
‘Meanwhile, if you made it to the letters-to-the-editor section of Wednesday’s (25 January) New York Times, you may have stumbled upon one reader’s rebuttal to a January 15 Times op-ed titled, “How ChatGPT Hijacks Democracy.”
The rebuttal was crafted—you guessed it—using ChatGPT: “It is important to approach new technologies with caution and to understand their capabilities and limitations. However, it is also essential not to exaggerate their potential dangers and to consider how they can be used in a positive and responsible manner.”’
Lisa Collins, is the vice president of marketing and communications at Akkodis Australia, and has previously worked at AWS, Publicis.Sapient and We Are Social.
ChatGPT cannot replace marketing communications staff completely. While ChatGPT can assist in generating creative ideas and written content, it lacks the human touch, empathy, and personal interaction skills that are essential in marketing and communications. Ultimately, effective marketing and communication require a combination of technology and human creativity, empathy, and strategy.
User ID not verified.
Open AI/ChatGPT will see the loss of up to 40% of current agency jobs within 2 years. There’ll still be good jobs for good people, but if AI can do it, AI WILL BE DOING IT. And there’s a lot of agency work AI can do as well [if not better], faster and cheaper right now.
User ID not verified.