Generative AI Has Come Quick: What’s Out, What’s Coming, and What to Consider.

A table of Generative AI tool options.

ChatGPT was released to the public six months ago and quickly became the fastest application to reach 100 million users. OpenAI reached this milestone in just two months compared to TikTok’s 9 months and Instagram’s 2 ½ years.

The result of this enormous attention is that the world has quickly become aware of the advanced capabilities of generative AI. As of March 2023, 87% of consumers had heard of AI and 61% somewhat understood what generative AI is and how it works.

ChatGPT generates text from text prompts through a chatbot, but that’s not all generative AI can do. The popularity of ChatGPT also brought attention to OpenAI’s image generation tool. DALL-E 2 generates images from text prompts through a chatbot.

A table listing and describing generative AI integration in major software platforms.
Which generative AI tools will you use for digital and social media marketing?

Despite the mass attention, AI tools have been around for years.

I first wrote about AI in a 2019 post “Artificial Intelligence And Social Media. How AI Can Improve Your Job Not Steal It.” In it, I talked about how AI was being used in algorithms, automation, machine learning, natural language processing, and image recognition.

That post also talked about how AI was used in chatbots to simulate human conversion, in predictive and prescriptive analytics, and in content generation. Examples included Patern89 which has been using AI to analyze content combinations and placement for optimization since 2016. Another example was Clinch which has used AI for content automation and personalized dynamic ad content across channels for years.

Since ChatGPTs release, there’s been a race to integrate generative AI.

The race began with ChatGPT being added to Microsoft’s Bing search engine. Then Google announced plans to integrate its generative AI Bard into Google search. Other platforms quickly announced integrations with OpenAI’s ChatGPT and Google’s Bard such as Salesforce, Hootsuite, HubSpot, and Adobe. Microsoft and Google are even integrating ChaptGPT and Bard into Microsoft 365 and Google Workspace office software for writing, spreadsheets, and slides.

Yet they’re not the only options. Other generative AI tools include Jasper.ai and Copy.ai, for writing, and Midjourney and Stable Diffusion for image generation. Tools like Synthsia generates videos with human avatars and professional voiceovers from text prompts. Other examples of generative AI are summarized below.

  AI content generation tool uses:

  • Content research/Data collection
  • Brainstorming/Idea generation
  • Copywriting/Copyediting
  • Summarizing/Note taking
  • Image (photo/illustration) generation
  • Video clip/Podcast clip generation
  • Transcript generation/Automated post prep
  • Ad/Post variation generation
  • Video generation
  • Podcast/Voice over generation
  • Presentation generation

Generative AI tools come with new skills and considerations.

A new skill with these next gen tools is prompt writing. Prompts are the natural language used to ask a generative AI tool to produce something. More descriptive specific prompts produce better results like prompts that describe the tone of writing or style of an image. Yet be mindful potential of copyright issues with prompts to create text or an image in the style of a famous person without their permission.

A new consideration is the data set from which you train AI. Generative AI tools like ChatGPT are trained on data from the open internet. This is what makes it so powerful, but this is also what can lead to copyright issues and sometimes create bias or incorrect results.

Other AI tools like Jasper.ai allow you to train on a specific dataset. For example, a brand could upload all its previous materials to establish a brand voice to write new copy. Adobe’s Firefly draws from Adobe’s stock library and tracks creator images used to ensure copyright compliance.

With the explosion of AI comes limitations and cautions.

Despite the mass adoption, this technology is in its early stages. There hasn’t been a lot of testing. Regulations, laws, and professional standards have yet to be developed. HubSpot suggests the following limitations, cautions, and warnings in using generative AI tools.

  Cautions when using generative AI:

  • AI can’t conduct original research or analysis.
  • AI can get things wrong so you must fact check.
  • AI doesn’t have lived experience and human insight.
  • AI doesn’t ensure quality, strategy, and nuance.
  • AI can contain biases that are not caught by filters.
  • AI can have plagiarism and copyright issues.

Despite these cautions, alarm over societal harm, and escalating calls for regulation, the AI race is on. Even while companies, government, and scientists raise concerns, companies continue to integrate AI into mainstream products and services. Below is a sample of what’s been released or announced thus far.

Examples of Early AI Content Generation and Automation Tools in Major Platforms.

Platform Tool Function
Hootsuite OwlyWriter AI Generates social media captions from URLs in different tone or voice, content ideas from prompts, auto recreation of top posts, and calendar events copy.
HubSpot Content Assistant Generate copy for blog posts, landing pages, emails and other content from idea to outline and copy generation.
ChatSpot Conversational bot that automates CRM tasks including status updates, managing leads, finding prospects, generating reports, forecasts, and follow-up drafts.
Salesforce Einstein GPT Auto-generates sales, service, and marketing tasks, content, targeting, messaging, reporting and personalization across channels.
Adobe Firefly Generate images, fill, text effects, and recolor from text prompts plus create content, and templates and edit video with simple text prompts – some inside Creative Suite.
Sensei GenAI Automates tasks, optimizes and generates content and content variations across channels in Adobe’s Experience Cloud marketing platform.
Canva Magic Write Generates copy, outlines, lists, captions, ideas, and drafts from text prompts.
AI Image Generator Generates images from text prompts and various styles and aspect ratios.
Meta AI Sandbox Tools that generate multiple versions of text and backgrounds, plus autocropping creative assets for various ad formats on Facebook and Instagram.
Grammarly GrammarlyGo
Generates writing and revisions relevant to tone, clarity, length, and task via text prompts in documents, emails, messages, and social media.
Microsoft Microsoft 365 Copilot Generates tasks, content, documents, presentations, spreadsheets, emails, reports, summaries, updates across Word, Excel, PowerPoint, Outlook and Teams via text prompts and Business Chat.
Google Google Workspace Bard Generate drafts, replies, summaries in Gmail, drafts, summaries, proofs in Docs, images, audio and video in Slides, auto analysis in Sheets, and notes in Meet.

Do Consumers (Your Customers/Target Audience) Want AI?

Another consideration with artificial intelligence is the value consumers may put on human generated content and transparency in the use of AI. I began this article by saying that 87% of consumers are now aware of AI. In fact, 4 in 5 of them are convinced that it is the future.

Yet knowing something is the future and wanting that future are different things. The same consumer survey reveals that 3 in 5 (60%) are concerned or undecided about that future. What people are most concerned about is that AI will change what it means to be human.

As marketing communications professionals we need to stay up to date with all these technology advancements. We should use the latest tools to improve our profession and results for our business or clients. But we should also ensure that new technology is used responsibly and transparently.

Over 77% of consumers say brands should ensure biases and systems of inequality are not propagated by AI-based applications. Over 70% believe brands should disclose when they use AI to develop products, services, experiences, and content.

You Decide How To Best Use AI.

At its best, AI can help with the mundane, repetitive tasks of social media and digital marketing management. At its best, AI will enable you to focus on higher level strategic thinking. At its best, AI will not replace humans, but enable us to be more human.

It’s been 6 months since generative AI was brought to mainstream awareness. Companies are rushing to integrate this technology into everything they do. While we wait for regulations, laws, and professional standards to catch up, let’s use our own judgment in deciding when, where, and how best to use it.

For my latest insights into AI, I began a blog series in Summer 2024 with

Artificial Intelligence Use: A Framework For Determining What Tasks to Outsource To AI [Template]

This Was Human Created Content!

Idea Writers Still Needed. What ChatGPT Can’t Do.

We’re going in on digital. If anyone doesn’t want to learn the Internet, pack up your desk and leave.

We heard this from the president of our ad agency during a Monday morning employee meeting. This may not be scary today when  65% of all ad spending is digital. But in the late-2000s it caused worry. Why?

As a mid-career advertising copywriter, I built my expertise on traditional mass media ads. I instinctively wrote print ads, billboards, 30-second TV scripts, and 60-second radio ads. That’s what I learned in undergrad, at Portfolio Center, and what I had created for 10 years. I honed my skills and was good at them. My campaigns with art directors helped clients meet sales objectives and won creative awards.

The Internet Experiment

I still remember that feeling. For us who built our careers on mass media ads, it was like the rug was pulled out from under our feet. Did I spend all those years in school and years fine tuning my craft only to be replaced by Internet experts? Would they need us traditional ad copywriters anymore? I remember Goodby, Silverstein & Partners, known for creative traditional ads, announced they were no longer an ad agency – they’re a digital agency. Advertising Age even ran an article with a subhead, “The Advertising Age Is Over.”

Source: “Digital Set to Surpass TV in Time Spent with U.S. Media,” eMarketer.com, August 1, 2013, http://www.emarketer.com/Article/Digital-Set-Surpass-TV-Time-Spent-with-US-Media/1010096 Note: Hours and minutes spent with each medium regardless of multitasking.

What did I do that Monday morning? I looked at a picture of my wife and kids on my desk. I needed the job and income, and decided to learn Internet marketing. I did and created many successful digital and social efforts for clients including PRSA social media word-of-mouth awards and OMMA online media marketing and advertising awards. Today I’m a professor, researcher, and author of digital and social media marketing. By 2017 AdAge ran another article, “Desktop and Mobile Ad Revenue Surpasses TV For The First Time.”

ChatGPT Experiment One

That feeling came back when ChatGPT was released. I had ChatGPT write a blog post for me, “Top 10 Tips For Successful Social Media Marketing: ChatGPT Wrote That Article In Less Than A Minute Then I Spend Four Hours Writing The Rest.”  It scared me how quickly it wrote an article that may take me hours based on years of experience.

I concluded that human-written articles do offer benefits beyond A.I. We form connections and develop bonds you don’t feel from a chatbot. Having a chatbot create your content can’t replace the rewards of learning on your own and developing your voice and unique perspective. Writing and creating are learning. That anxious feeling subsided.

ChatGPT Experiment Two

Then the editor of our student magazine approached me with an idea. He wanted ChatGPT to complete a class assignment. I convinced myself I could do better writing on my blog, but what about a student report? If ChatGPT could do it why am I needed as a professor? There was that feeling of the rug being pulled out again.

Create A Situation Analysis for Spotify

For Marketing Principles, a key assignment is to write a situation analysis for a company. Students select the company with stipulations to ensure they’re accessing the kind of data that professional markers use to create their marketing strategies. Our university has databases such as Mintel and Statista so students can learn more by doing. Below is a general description:

Select a US product/service you’re interested in and conduct a situation analysis on the current marketing environment. Write an introduction, access a Mintel report (define the market, describe key trends, select one company in the market), assess the internal environment, assess the external environment, create a SWOT summary graphic, create marketing objectives (following SMART guidelines), a value proposition, and a conclusion. Use APA format with all sources cited in APA Style.

He instructed ChatGPT to write a situation analysis for a company in the streaming audio market in APA style and gave it my specific requirements. ChatGPT chose Spotify.

Introduction

For the introduction, ChatGPT wrote:

The streaming audio industry has experienced significant growth in recent years, driven by increasing demand for on-demand audio content and advancements in technology. As a result, companies like Spotify have been able to capitalize on this trend and achieve impressive growth in terms of user base and revenue.

From this intro., it sounds like ChatGPT is accessing the right data and understands the purpose of the report and assignment.

Access Mintel Market Report

While what ChatGPT said is true, I would look for more in a student report. I ask them to summarize some of the latest trends that would be important to form a marketing strategy. According to the latest Mintel report “Streaming Audio – US – 2022,” there is more a marketer would need to know. Even the first paragraph of Mintel’s report highlights trends in the market that may influence Spotify’s marketing strategy:

  • 2/3rds of customers want help choosing what to listen to via curated content.
  • Exclusive/early access to new music, podcasts, and audiobooks can differentiate.
  • 62% of adults try to support services that fairly compensate artists and creators.

Internal Environment

For the internal environment, ChatGPT did a good job pulling the company mission statement from its website and describing the basic service. It even provided what looks to be an APA citation:

Spotify was founded in 2006 in Stockholm, Sweden, and has since become a leading global streaming audio platform. The company’s mission is to “unlock the potential of human creativity by giving a million creative artists the opportunity to live off their art and billions of fans the opportunity to enjoy and be inspired by it” (Spotify, n.d.). Spotify’s primary product is its music streaming service, which is available to users on desktop and mobile devices, as well as through connected devices such as smart speakers.

ChatGPT does go on to provide some marketing performance numbers:

Spotify has over 365 million monthly active users, including 165 million premium subscribers (Statista, 2021).

The first number seems accurate, but there are more current numbers as of Q4 2022 from Statista of 489 million monthly active users (MAUs) and 205 million premium subscribers. I would expect students to find the latest data. A 124 million, 34% increase for MAUs and 40 million, 24% increase for premium subscribers is significant.

Then ChatGPT reports a revenue number:

The company has experienced significant growth in revenue, with a 16% increase in 2020 to $7.88 billion (Spotify, 2021).

The revenue number looks correct until you do some research and find the number is in euros, not US dollars. Spotify is a European company, but the assignment is to focus on the US market. To report revenue with a US dollar sign, which ChatGPT did, it should be around $8.47 billion. I also found a more recent 2022 revenue number of 11.72 billion euros or roughly $12.41 billion US dollars. The conversion difference is $59 million, the date difference is nearly $3.94 billion.

Lastly, under the internal environment, ChatGPT names Spotify’s main competitors:

However, Spotify faces challenges from competitors such as Apple Music, Amazon Music, and Pandora.

This sounds reasonable, but in Mintel’s report a graph shows Spotify’s close competitors as (1.) YouTube Music and (2.) Pandora. Because ChatGPT isn’t using real citations it’s hard to know where it got this and how old it is. Understanding current competitors is important to any strategy.

External Environment

For external environment, ChatGPT wrote:

Political, legal, and economic factors impacting Spotify’s marketing performance include issues related to copyright law and licensing agreements, as well as the impact of the COVID-19 pandemic on the music industry. Demographic, social, and cultural factors impacting Spotify include changing music consumption habits and the increasing popularity of podcasts. Technological factors include the development of new platforms for streaming audio, as well as advancements in artificial intelligence and machine learning that are used to make personalized recommendations.

This is a good general list of issues that may affect Spotify and the streaming audio market, but there are no details that could turn into insights actionable in a marketing strategy. COVID-19 impacted the music industry, like all industries, but how? Mintel’s report explains how and indicates its negative impact was less than expected:

  • Growth slowed, but people found ways to listen to their favorite music and podcasts.
  • The low barrier to publishing helped artists publish even from home.

An important external factor missing from ChatGPT’s list is inflation – something Spotify needs to consider for product, pricing, and promotion strategies. The Mintel Report warns that high inflation of 8-9% in the past year could lower household spending on streaming audio with a large percentage of adults worried about rising prices.

The next requirement was to summarize what was found in a SWOT graphic of internal strengths and weaknesses, plus external opportunities, and threats.

SWOT Summary Graphic

Below is what ChatGPT provided:

The SWOT analysis for Spotify is presented in the figure below.

Obviously, it didn’t draw the graphic. I am not sure what it tried to access from Imgur.com. If It did find a Spotify SWOT from Imgur it wouldn’t meet my requirements. That would be someone else’s SWOT based on their opinion and data, not a summary of what the student found in their situation analysis.

Marketing Objective

Next, ChatGPT wrote a marketing objective:

To continue its growth in revenue and premium subscribers, Spotify should set the following marketing objective: “Increase premium subscribers by 20% over the next marketing budget year, from 165 million to 198 million, through targeted marketing campaigns and promotions.”

This objective meets some SMART guidelines. It’s specific, measurable, achievable, and time-bound. But it’s not relevant since there’s more recent data. They’ve surpassed this revenue objective.

I would also coach students about using global numbers versus market-specific numbers. Typically, marketers set objectives for different markets like the US or North America vs. Europe to set unique marketing plans for each. From Statista 28% of Spotify’s premium subscribers are from North America (57.4 million), from which you could set a more accurate marketing objective.

My bigger apprehension about ChatGPT’s marketing objective is that it might not be right based on what we learned from Mintel about concern over inflation. If most people are worried about rising prices can Spotify convince 33 million more people to add a premium subscription while not losing any existing premium subscribers?

A revenue or market share objective may be better to grow all users by promoting free and premium accounts. Spotify makes advertising revenue from free accounts. You don’t want a loss to competitors. This would depend on what we find out about the main competitor(s) and what they are offering, which ChatGPT didn’t describe.

Value Proposition

For the value proposition, ChatGPT wrote:

Spotify’s value proposition is based on its ability to provide users with a comprehensive library of music and audio content, delivered through a user-friendly platform that enables easy discovery and sharing. With a focus on user engagement and social sharing, Spotify encourages loyalty and helps users discover new music and artists that fit their tastes, while also providing access to popular hits and classic tracks.

At first, this sounds like a good value prop. But it’s more a general product description that could apply to any competitor in the streaming audio market. From a student, I’d look for a more nuanced understanding of the current market, consumer trends, and competitors. The value proposition should take into consideration Spotify’s unique place in the market in comparison to what competitors are offering and what consumers are currently looking for.

Conclusion

This was ChatGPT’s conclusion:

In conclusion, Spotify is well-positioned to continue to succeed in the rapidly growing streaming audio market, despite facing challenges from competitors and changing market trends. Developing effective marketing strategies and objectives is critical for Spotify to maintain its position as a leader in the industry. By leveraging its unique value proposition and focusing on key marketing metrics, such as premium subscriber growth, Spotify can continue to drive revenue and capture market share.

This sounds like a good conclusion, but there’s no real understanding of the current streaming audio market. It makes it sound so easy! Yet, if marketers relied on past/current offerings and never made adjustments based on changing market conditions, consumer trends, and competitor actions they wouldn’t be well-positioned to continue to succeed.

References

This was ChatGPT’s references:

References

Spotify. (n.d.). About Spotify. Retrieved August 29, 2021, from https://www.spotify.com/us/about-us/

Spotify. (2021). Spotify Technology S.A. fourth quarter and fiscal year 2020 financial results. Retrieved fromhttps://www.sec.gov/Archives/edgar/data/1639920/000163992021000014/spotify2020q4ex991.htm

Statista

It hasn’t provided references to the multiple Statista data with URL links. The required Mintel market report is missing. ChatGPT seems to be mimicking some aspects of APA citation but missing a lot.

My Overall Assessment?

This report looks into the past, describes Spotify as is, sets a higher premium subscriber number, and says to keep doing what you’re doing to succeed! There’s no real understanding. It feels like a collection of incomplete facts organized into categories and written to sound like a person talking. I wouldn’t base my marketing strategy on it! If a student was hired into the marketing department at Spotify and their manager asked them to submit a situation analysis, I would not want them to submit this.

From my experience so far ChatGPT answers lack human nuance, insight, and refinement. Plus, if ChatGPT can answer it alone, why would a company, client, or audience need you? That’s what we all need to figure out. ChatGPT can be a great tool to jumpstart your thinking, but what are you good at that ChatGPT can’t do?

What Am I Good At?

Back in the late 2000s, I found the answer in Teressa Iezzi’s book The Idea Writers. She reminded copywriters and art directors (creators) that we weren’t experts at traditional ads. We were really writers and designers of ideas that connect brands to consumers no matter the tool. We’re experts in human truths and crafting stories that connect with target audiences through emotion to meet marketing objectives.

I could have had ChatGPT write this entire article, but I don’t think it would have the same relevance, reach, and resonance. Can you relate to the feelings I’ve had (in my past and current career)? How’s your anxiety over ChatGPT as a writer, designer, creator, marketer, student, or professor?

Look for Ethan Dyril’s article coming out in the Swinging Bridge on March 31st.