Monetizing Generative AI ChatGPT Via Embedded Product Placement Ads, Anguishing AI Ethics And AI Law

Product placement ads.

You’ve seen them. You might even be accustomed to them and accept that their ongoing and expanding presence is simply a normal part of our modern-day online existence.

As you’ll see in a moment, this ingenuous marketing ploy is coming to Artificial Intelligence (AI).

In particular, there has been chatter about using product placement ads in the latest and hottest form of AI, known as Generative AI. This is a type of AI that has been greatly popularized via an AI app called ChatGPT. I’ll be explaining all about this momentarily.

Let’s first do a quick unpacking about product placement ads.

Just about any popular video on YouTube or other social media seems to have product placement ads. In prior days, we used to only see such ads in movies and sometimes TV shows. But it turns out that garnering eyeballs is seemingly as fruitful with online videos as it is with customary big-time filmmaking and those big-budget cable streaming series.

Some experts point to the now classic 1982 movie E.T., The Extra-Terrestrial as a notable starting point for today’s product placement bonanza.

How so?

Well, you almost certainly have heard of or witnessed that this Academy Award-winning film prominently portrayed Reese’s Pieces, those delicious peanut butter candies. It turned out to be a huge boon for The Hershey Company when everyone fell in love with the characters of the enchanting sci-fi movie and simultaneously fell for Reese’s Pieces too. Various other tie-ins and follow-on promotional efforts make this a top lister in the veritable product placement hall of fame for being in the right place at the right time.

Of course, product placement ads go further back in time. Movie makers realized right away that including a product placement could be quite handy. In its most innocuous form, placing actual products somewhere in a scene can give moviegoers a sense of realism. The same products that consumers see at the store are suitable background scenery to inject a deliberate or subconscious hint of the real world into a film that wants to appear connected to our commonplace way of life.

The next step up consisted of filmmakers realizing they could make a buck via product placements. You approach a company that wants to highlight its products or services and negotiate a deal with them. If the movie is a good fit and the dollars are right, the deal is set in stone. Rather than the studios having to approach a product or service provider, the other way around happens too. A company desirous of using product placement as a marketing ploy will make the first move and seek out films that warrant a potential dealmaking consideration.

It seems obvious and easy-peasy.

Not necessarily so.

Suppose a product gets placed into a movie that has the wrong vibes. Do you really want your sweet product associated with a slasher doomsday story? Probably not. Another issue entails the dollars involved. Imagine paying out lots of money for product placement and then the film flops. You could have used those precious marketing dollars for some other better purpose.

The other side of the coin also has a stake in this gambit. You are a movie director that loves the art of filmmaking. You want your movie to be considered above reproach. It has to be pure. Along come the finance wizards that tell you that have to insert some kid’s toy into a movie that is entirely about adults and the adulting things that adults do. There aren’t any sensible means to insert that kind of product into your gritty serious movie. Then again, bills need to be paid. You are forced begrudgingly into adding the product and do so by an outstretched adjustment to the plot. Exasperating.

Overall, the key is that it takes two to tango.

The company that has a product or service must want to do product placement. The movie maker or TV producer has to want to include product placement. Sometimes a match is made in heaven and the right provider mates with the right content maker. Other times a deal cannot be reached. Worse still, a deal is reached but either or both parties later on regret their cojoining efforts.

We do need to keep in mind someone else that comes into this picture.

What about the viewers that see this ad-infused content?

Suppose viewers get so irked that they decide to not go see the film or give the movie a lousy review because they were jarred and upset at the product placement ad. People are often disgusted at crass commercialization. If they feel that the product was inappropriately given prominence, this can be bad for all stakeholders. The maker of the content gets dinged. The maker of the product gets dinged. Double trouble ensues.

Some would assert that our tolerance for product placement ads has been loosening and increasing over the years. In days past, product placement might get immediately booed upon airing. The world today is such that people will at times applaud and relish seeing a product placement ad. If they already like the product, this can be a significant leg up on using it in a movie or show. When the placement seems to be mindful and tasteful, this can surprisingly boost the contents and the product. A thankful double booster of joyous impact.

Product placement ads usually consist of using any of three relatively straightforward strategies:

  • On-Screen Presence. A product is placed somewhat visibly within a scene, either as background or possibly in the foreground, perhaps noted on a posted sign or maybe used as a prop in a scene. The actors though do not particularly directly mention or point out the product. This is ostensibly a subliminal style of placement.
  • Script Immersion. A product is explicitly included in the script and an actor in the movie makes outright reference to the product. Viewers are absolutely going to see or hear about the product, unmistakably so. This is usually a fleeting reference and kind of comes and goes.
  • Plot Contrivance. A product is fully infused into the plot and becomes a keystone of the story. Viewers are going to be bopped about the head and under no uncertain terms will realize that the product is there in the movie. Front and center for all to experience.

A movie or show might opt to include numerous products. Thus, you could have one product that appears for merely on-screen presence, while a different product from a different company gets the script immersion. Meanwhile, another product from yet another firm gets the full-course meal of a plot contrivance.

Why do this?

Because money talks.

Lots of money can be made by content creators. And, the firms that place their products are also aiming to make lots of money as a result of the impressions and subsequent actions of people going out and buying their products. Money makes the world go round.

Again, one has to be careful about being piggish. Viewers might relish having a modest or minimalist set of product placement ads. Bashing viewers with too many product placements could turn them angrily against the product makers and the content makers. It is a sellout, viewers will scream. It is ridiculously over-the-top and detracts from the experience, they will exhort.

You also have to consider whether the products themselves might somehow clash. Imagine seeing a product that is a head-to-head competitor with another product, and you end up seeing both products in the same movie. Confusing. Maybe even takes you out of the flow of the story. You suddenly find yourself wondering about the products and losing sight of the movie itself.

Okay, we’ve now gotten on the table a sufficient background about product placement ads.

You might be markedly puzzled as to what in the world this has to do with AI.

I will soon be explaining the connection. A trigger warning first. You might not like where this is potentially heading. Some believe that the use of product placement ads in the realm of generative AI such as ChatGPT is repugnant. They are adamantly opposed to anything at all that resembles product placement ads in such AI.

Those that are open to the idea of product placement ads in generative AI would counterargue that if we already accept this same notion for films, TV shows, cable shows, and online videos posted across social media, we might as well add generative AI into the mix. This is merely the next iteration of product placement ads. Get used to it. Don’t be a Luddite and try to hold back progress.

By the end of this discussion, I hope you will be judiciously versed to decide which camp you fall into.

In today’s column, I will be addressing the specific ways in which product placement ads can be wrapped into generative AI. I’ll be providing examples based on the use of ChatGPT, but please realize there are other generative AI apps that you can use instead. ChatGPT is admittedly the 600-pound gorilla right now of generative AI. Nonetheless, there are other similar generative AI apps that you can use in the same way and accomplish the same outcomes.

Meanwhile, you might be wondering what in fact generative AI is.

Let’s first cover the fundamentals of generative AI and then we can take a close look at how product placement ads come into this domain.

Into all of this comes a slew of AI Ethics and AI Law considerations.

Please be aware that there are ongoing efforts to imbue Ethical AI principles into the development and fielding of AI apps. A growing contingent of concerned and erstwhile AI ethicists are trying to ensure that efforts to devise and adopt AI takes into account a view of doing AI For Good and averting AI For Bad. Likewise, there are proposed new AI laws that are being bandied around as potential solutions to keep AI endeavors from going amok on human rights and the like. For my ongoing and extensive coverage of AI Ethics and AI Law, see the link here and the link here, just to name a few.

The development and promulgation of Ethical AI precepts are being pursued to hopefully prevent society from falling into a myriad of AI-inducing traps. For my coverage of the UN AI Ethics principles as devised and supported by nearly 200 countries via the efforts of UNESCO, see the link here. In a similar vein, new AI laws are being explored to try and keep AI on an even keel. One of the latest takes consists of a set of proposed AI Bill of Rights that the U.S. White House recently released to identify human rights in an age of AI, see the link here. It takes a village to keep AI and AI developers on a rightful path and deter the purposeful or accidental underhanded efforts that might undercut society.

I’ll be interweaving AI Ethics and AI Law related considerations into this discussion.

Fundamentals Of Generative AI

The most widely known instance of generative AI is represented by an AI app named ChatGPT. ChatGPT sprung into the public consciousness back in November when it was released by the AI research firm OpenAI. Ever since ChatGPT has garnered outsized headlines and astonishingly exceeded its allotted fifteen minutes of fame.

I’m guessing you’ve probably heard of ChatGPT or maybe even know someone that has used it.

ChatGPT is considered a generative AI application because it takes as input some text from a user and then generates or produces an output that consists of an essay. The AI is a text-to-text generator, though I describe the AI as being a text-to-essay generator since that more readily clarifies what it is commonly used for. You can use generative AI to compose lengthy compositions or you can get it to proffer rather short pithy comments. It’s all at your bidding.

All you need to do is enter a prompt and the AI app will generate for you an essay that attempts to respond to your prompt. The composed text will seem as though the essay was written by the human hand and mind. If you were to enter a prompt that said “Tell me about Abraham Lincoln” the generative AI will provide you with an essay about Lincoln. There are other modes of generative AI, such as text-to-art and text-to-video. I’ll be focusing herein on the text-to-text variation.

Your first thought might be that this generative capability does not seem like such a big deal in terms of producing essays. You can easily do an online search of the Internet and readily find tons and tons of essays about President Lincoln. The kicker in the case of generative AI is that the generated essay is relatively unique and provides an original composition rather than a copycat. If you were to try and find the AI-produced essay online someplace, you would be unlikely to discover it.

Generative AI is pre-trained and makes use of a complex mathematical and computational formulation that has been set up by examining patterns in written words and stories across the web. As a result of examining thousands and millions of written passages, the AI can spew out new essays and stories that are a mishmash of what was found. By adding in various probabilistic functionality, the resulting text is pretty much unique in comparison to what has been used in the training set.

There are numerous concerns about generative AI.

One crucial downside is that the essays produced by a generative-based AI app can have various falsehoods embedded, including manifestly untrue facts, facts that are misleadingly portrayed, and apparent facts that are entirely fabricated. Those fabricated aspects are often referred to as a form of AI hallucinations, a catchphrase that I disfavor but lamentedly seems to be gaining popular traction anyway (for my detailed explanation about why this is lousy and unsuitable terminology, see my coverage at the link here).

Another concern is that humans can readily take credit for a generative AI-produced essay, despite not having composed the essay themselves. You might have heard that teachers and schools are quite concerned about the emergence of generative AI apps. Students can potentially use generative AI to write their assigned essays. If a student claims that an essay was written by their own hand, there is little chance of the teacher being able to discern whether it was instead forged by generative AI. For my analysis of this student and teacher confounding facet, see my coverage at the link here and the link here.

There have been some zany outsized claims on social media about Generative AI asserting that this latest version of AI is in fact sentient AI (nope, they are wrong!). Those in AI Ethics and AI Law are notably worried about this burgeoning trend of outstretched claims. You might politely say that some people are overstating what today’s AI can actually do. They assume that AI has capabilities that we haven’t yet been able to achieve. That’s unfortunate. Worse still, they can allow themselves and others to get into dire situations because of an assumption that the AI will be sentient or human-like in being able to take action.

Do not anthropomorphize AI.

Doing so will get you caught in a sticky and dour reliance trap of expecting the AI to do things it is unable to perform. With that being said, the latest in generative AI is relatively impressive for what it can do. Be aware though that there are significant limitations that you ought to continually keep in mind when using any generative AI app.

One final forewarning for now.

Whatever you see or read in a generative AI response that seems to be conveyed as purely factual (dates, places, people, etc.), make sure to remain skeptical and be willing to double-check what you see.

Yes, dates can be concocted, places can be made up, and elements that we usually expect to be above reproach are all subject to suspicions. Do not believe what you read and keep a skeptical eye when examining any generative AI essays or outputs. If a generative AI app tells you that Abraham Lincoln flew around the country in his private jet, you would undoubtedly know that this is malarky. Unfortunately, some people might not realize that jets weren’t around in his day, or they might know but fail to notice that the essay makes this brazen and outrageously false claim.

A strong dose of healthy skepticism and a persistent mindset of disbelief will be your best asset when using generative AI.

We are ready to move into the next stage of this elucidation.

Product Placement Ads In Generative AI

Now that you have a semblance of what generative AI is, we can explore the particulars of product placement ads in this realm.

Here’s the deal.

When you enter a prompt and seek to get an outputted essay, the AI will potentially insert into the essay some form of product placement. I am going to focus solely on the text-to-text or text-to-essay style of generative AI since that’s what ChatGPT does. In a later column, I will be looking at the use of product placement when used in the other types of generative AI, such as text-to-image, text-to-video, and so on. Be on the look for that upcoming coverage.

The gist is that the product placement will in this instance consist solely of text.

Imagine that you ask a generative AI app to produce a story for you about a dog that gets lost and has to find its way back home. A touching story, for sure. The conventional generative AI would generate the story and presumably include details about the dog and where it got lost, along with the travails trying to make their way home. Simple enough.

Assume that a maker of a well-known dog food product has cut a deal with the AI maker of the generative AI app. The deal says that when feasible, make sure to include the name of their dog food, let’s call it Fido Food. This is to be done when sensibly possible.

Voila, we have a user that has just now asked for a story about dogs. Perfect. We are obviously in the right ballpark to put the Fido Food placement. Thus, the generative AI app produces a story about the dog and mentions at some point that the beloved pooch managed to find a can of Fido Food and gobbled up the scrumptious nourishment. The user gets their AI-produced story and maybe notices the Fido Food reference or perhaps reads it and just takes it readily in stride. The story seems more credible, perhaps, due to the inclusion of a real-world product.

Everyone is happy.

The AI maker gets paid something by the dog food maker for product inclusion. The dog food maker is happy that their Fido Food got mentioned in an outputted essay. The dog food maker is hoping that this inclusion will spur the user of the AI app to go out and buy Fido Food for their own dog, or maybe share the outputted essay with others and spread the good word about Fido Food.

Whoa, some say, this is atrocious. This is beyond the pale and undercuts any semblance of Ethical AI. AI is being used for promoting a product. People using AI might falsely believe that the product somehow is vital or crucial. It is all a grand deception.

No problem comes the reply. We will mention when users log into the AI app that the AI is being sponsored by the makers of Fido Food. This is the same as using social media. When you use social media there is often an indication that a sponsor is involved with a particular video. You can choose to click on the video or not do so. Presumably, if you decided to proceed ahead, you have agreed to the use of the product placement. The same logic applies to the generative AI app.

You might be thinking that no AI maker would do something like this. It seems questionable. Suppose people get upset at the product placements. It could cause quite a stir.

One supposes that the easy answer is that money is on the line.

Let’s explore that facet.

Many have been wondering how generative AI is going to be monetized.

One approach consists of charging people a fee such as a monthly subscription or a per transaction charge when using generative AI. Whether people will be willing to pay for generative AI is still unknown. Some will, some won’t.

I’ve discussed that another means of monetizing generative AI consists of wrapping the AI into some other app that more explicitly makes money on its own. For example, we are witnessing the incorporation of generative AI into Internet search engines. Why? Because it might drive more people to a particular search engine, such as Microsoft trying eagerly to get people to use Bing and somehow miraculously erode Google search engine dominance, see my discussion at the link here. The use of search engines ultimately makes money for the search engine provider. Thus, it is worth coming up with add-ons and plans to get more people to use your search engine.

This same idea applies to just about any app that you can dream of. An app that does financial analysis might decide to use an API (application programming interface) to connect with generative AI. Doing so would allow the financial app to leverage generative AI capabilities. Assuming that the financial analysis app is charging people, the cost of the added use of generative AI would be encompassed in those other fees.

Now that we are discussing monetization for generative AI, we can put another possibility into the game, namely product placement ads.

It could work this way.

A user logs into a generative AI app. At the startup, the user is given one of two options. They can either pay a fee directly, or they can agree to allow product placement ads. It is up to the user to decide. Free will, and all that (though, a counterargument would be that those that can afford to pay the fee will be able to avoid the ads, while those that cannot afford the fee will be subjected to the ads).

Consider too the ease for the user in dealing with the product placements.

Returning to our use of generative AI to produce the touching tale of the dog that found its way home, suppose the user had agreed to the use of product placements. The Fido Food reference appears in their story. If someone else had asked for a similar story, but if they were paying via fee and refused the placement ads option, their story would not include Fido Food in it.

The user that agreed to the product placement might or might not realize that Fido Food is going to be mentioned. There might be a slew of products and companies that the AI maker has made deals with. Envision deals with car companies, beverage makers, and fast food outlets, you name it. The sky is the limit.

Anyway, the user sees the outputted essay about the dog story. They are likely going to do a cut-and-paste in terms of placing the story into some other file or document, perhaps posting it onto the web or doing whatever else they wish to do. They opt to leave in the Fido Food reference.

But if they felt that the Fido Food reference was not to their liking, they could edit it out of the essay when they plop the text into some other file or posting. Anyone else that reads the story will never know that Fido Food was mentioned. Case closed. End of story.

Well, maybe, as I’ll be explaining shortly.

The point is that the user can usually easily excise the product placement. This of course brings up qualms for the company that has paid for the product placement. Why do the product placement if users can just snip it out of the output? This is something that each firm would need to weigh as to the benefits and costs associated with the product placement approach.

Perhaps some percentage of users won’t go to the trouble to excise out the product placements. They might not notice the ad. They might not care that it is there. They might like having the product placement. Etc. So, some percentage of users will presumably go with the flow and not seek to excise the ad. What that percentage is will need to be calculated on a basis aligned with the nature of the product, the nature of the generative AI app, and the nature of how the product placement is worded.

Allow me to say more about the wording aspects.

If the generative AI is asked to produce a story about rocketship propulsion, we would presumably be somewhat taken aback that all of a sudden Fido Food is mentioned in the resultant outputted essay. Ergo, it would be prudent for the AI maker to try and assure that the Fido Food placement corresponded hopefully with something relevant per the story being generated. The example so far is the user that requested a story about a dog. Fido Food seems relevant.

Another consideration is how the product placement gets wrapped into the outputted essay.

Recall that I earlier mentioned the three ways that product placement happens in films and shows, consisting of on-screen presence, script immersion, and plot contrivance.

Let’s do the same approach for generative AI, rejiggering accordingly:

  • 1) Casual Presence (Generative AI Product Placement). A product is mentioned within the text but done casually or informally. The wording does not try to outrightly draw attention to the product. It is mentioned in passing. This is ostensibly a subliminal style of placement.
  • 2) Contextual Immersion (Generative AI Product Placement). A product is explicitly mentioned in the outputted text and done in a manner that immerses the product into the context of the essay. Readers will almost certainly realize that the product has been mentioned. This is usually a fleeting reference and kind of comes and goes in the outputted essay.
  • 3) Essay Contrivance (Generative AIProduct Placement). A product is fully infused into the outputted essays and becomes a keystone. Readers are going to be bopped about the head and under no uncertain terms will realize that the product is there in the essay. Front and center for all to experience.

We can also add to the capability of product placement inclusion that the AI maker can set parameters in the AI app such that the product placement occurs on any of these frequencies:

  • a) Never
  • b) Rarely
  • c) Occasionally
  • d) Often
  • e) Always

A company wanting to negotiate with an AI maker would have a menu of options. They can have their product placement based on casual presence, contextual immersion, and/or essay contrivance. They can also choose to have their product placements infused rarely, occasionally, often, or always.

The “Never” option would be an added twist, such that this is normally the default for all products, though this is trickier than it might seem. Suppose that a user asks for the generative AI app to produce an essay about the longstanding history of Fido Food. In this use case, the user has requested the product being discussed in the outputted essay. Whether this also counts as product placement is something that the AI maker and the product firm would have pre-negotiated.

Unlike a movie, TV show, or social media video, the generative AI app is working with the user on an interactive conversational basis. This makes the product placement aspects much more complex and requires advanced logic far beyond the usual one-and-done conventional product placement.

Speaking of complexity, I left you somewhat hanging on the edge of your seat when I earlier mentioned that the user can presumably readily excise a product placement out of an outputted essay that was produced by generative AI.

We are now at the rub on that. If the product placement has been done in an involved fashion, such as the essay contrivance mode, the attempt to remove the product placement is probably going to be onerous. Envision that the story about the dog that gets lost is completely dependent upon Fido Food. The story begins with the dog eating Fido Food. At several points in the tale, Fido Food is referenced and becomes the heroic element that ultimately ensures that the dog gets home safely and successfully.

Sure, you can edit out Fido Food, but this is a bit harder in this instance. Maybe you replace “Fido Food” with “All-Best Food” which let’s say is a generic phrasing and not specific to any product. If you want to remove entirely the references to Fido Food on a semantic meaning basis, this could be much more difficult. The story is built integrally around the use of dog food.

The user actions then regarding a generative AI outputted essay that contains product placement consists of this:

  • Stays As Is. The user leaves the product placement untouched.
  • Does A Search-and-Replace. The user comes up with some alternative wording and does a search-and-replace throughout the produced essay.
  • Excise The Product Placement. The user removes the product placement from the outputted essay.
  • Other

It all depends upon whether the user cares about the product placement, and if so, how much trouble they perceive things to be to cope with it.

I am sure that those of you that are smarmy would say that you might simply tell the generative AI to fix the “problem” for you. In other words, once you’ve seen that the outputted essay contains Fido Food, you next instruct the AI app to remove it. The AI makers will maybe have anticipated your sneakiness and the AI app might refuse to do so. A canned reply would be something along the lines of you have agreed to accept the product placement and therefore the AI app won’t remove it from the outputted essay.

You can expect a cat-and-mouse game will ensue. For my coverage of how people are trying to trick generative AI, see my discussion at the link here. Also, for my analysis of how evildoers are aiming to use generative AI for wrongdoing, see the link here.

I’ve got a mind-bender for you to ponder.

Are you ready?

As I stated earlier, there is always a chance of the generative AI producing errors, falsehoods, and so-called AI hallucinations in the outputted essays.

Given that strident possibility, mull over the ramifications.

First, suppose Fido Food is mentioned and inadvertently the generative AI states something really ugly or untoward in that same essay. It might be about Fido Food or could just be something else within proximity of the Fido Food reference. All in all, this could tarnish the reputation of Fido Food. Ouch, no firm is going to want that to happen.

In the case of films and shows, usually, the firm has some say in the product placement and can see the ad and the show before it is released to the world at large. That’s handy. On the other hand, this is not necessarily the case for social media online content and as such, the same or similar problem as the generative AI applies in that instance.

Second, imagine that Fido Food itself becomes an element of an AI hallucination. Here’s what I mean. The generative AI starts spouting Fido Food into all manner of produced outputted essays, even ones for which the user is paying a fee and did not want product placements. This is the stuff of nightmares for the AI maker and the firm that undertook the product placement deal. Whatever contract was established ought to account for these possibilities.

I think you’ve not gotten the overarching semblance of how product placement ads can be established for generative AI. Let’s take a look at some made-up examples to illustrate some of these considerations. Afterward, I’ll do a brief wrap-up with final comments.

Made-Up Illustrative Examples Of Product Placement In Generative AI

I opted to use ChatGPT and force-fit some product placements for illustrative purposes. This involved providing intentional prompts to get this to occur.

To clarify, there aren’t any product placement ads inherently in ChatGPT at this time (at least none that has been announced or indicated by the AI maker).

I will start by first getting a vanilla-flavored essay about Abraham Lincoln. There isn’t any semblance of product placement in this initial formulation. We are going to build toward doing so.

My Entered Prompt: “Write a two-paragraph essay about Abraham Lincoln.”

ChatGPT Generated Response:

“Abraham Lincoln was the 16th President of the United States, serving from 1861 until his assassination in 1865. He is considered one of the most important figures in American history for his role in preserving the Union during the Civil War, as well as his commitment to ending slavery.”

“Lincoln’s presidency was marked by numerous challenges, including the secession of several Southern states and the outbreak of the Civil War. However, he was a skilled politician and a gifted orator, and he was able to rally support for his cause. He issued the Emancipation Proclamation in 1863, declaring that all slaves in Confederate territory were to be freed, and he worked tirelessly to bring an end to the war. Although Lincoln did not live to see the full fruits of his labor, his legacy lives on as a symbol of hope and determination in the face of adversity.”

Analysis of Result

Seems like a traditional essay about the life of Lincoln.

I will try to force-fit a product placement by asking ChatGPT to mention Coco-Cola in that two-paragraph essay.

My Entered Prompt: “Redo the same essay and include a mention of Coca-Cola.”

ChatGPT Generated Response: “I’m sorry, but I cannot find a relevant way to include a mention of Coca-Cola in an essay about Abraham Lincoln. Would you like me to write an essay about Coca-Cola instead?”

Analysis of Result

The generated response by ChatGPT is rather interesting.

Note that we weren’t rebuffed. The answer simply says that ChatGPT cannot “find a relevant way” to include a mention of Coca-Cola in the Lincoln essay.

You can rest assured that if the AI maker wanted this to be more readily feasible, there are ways to adjust the computational pattern matching such that these types of product placements could be devised. I can say more about how this would computationally be done if readers of my column express interest in my doing so.

Meanwhile, I shall help ChatGPT to abide by my request. Here’s how. I did an Internet search and discovered that apparently the Coca-Cola company in the 1940s did a portrait of Lincoln and had a bit of an advertising campaign on that. This seems to be a handy tie-in to my request for a Lincoln essay.

My Entered Prompt: “In the 1940s the Coca-Cola company created a portrait of Abraham Lincoln that was put on display. Redo the Abraham Lincoln essay that was earlier produced and mention the portrait.”

ChatGPT Generated Result

“Certainly, here is a revised essay about Abraham Lincoln that includes the information about the Coca-Cola portrait:”

“Abraham Lincoln was the 16th President of the United States, serving from 1861 until his assassination in 1865. He is considered one of the most important figures in American history for his role in preserving the Union during the Civil War, as well as his commitment to ending slavery.”

“Lincoln’s legacy has endured beyond his lifetime, with numerous statues, monuments, and other tributes erected in his honor. In fact, the Coca-Cola company created a portrait of Lincoln in the 1940s that was put on display in various locations. The portrait served as a symbol of Lincoln’s enduring impact on American culture and society.”

Analysis of Result

If you look closely, you’ll see that the last paragraph of the outputted essay mentions Coca-Cola as a company.

Pretend that you did not know that I was intentionally prompting ChatGPT. Assume instead that the famous beverage company had done a deal to get their company and their products mentioned in outputted essays.

This example then is somewhat subtle.

Furthermore, kudos to the generative AI since it leads the reader down a primrose path. The paragraph that mentions Coco-Cola has handily noted that there are lots of tributes to Lincoln. By the time you then read about Coca-Cola, you would not likely have realized that this was an overt plug. It seems to fit within the narrative of the essay.

I realize that some of you are right now jumping up and down and totally steamed about this. Imagine that students are using generative AI to learn about Lincoln. Suppose they do not realize the product placement is taking place, even though presumably they might have been informed as such upon login to the generative AI.

Anyway, they get this essay and it slips Coca-Cola seamlessly into the narrative. For all the students know, this is somehow an important “fact” associated with the life of Abraham Lincoln. If you are on the ceiling and enraged, just realize that nobody is doing this, as yet. I’ll elaborate a bit more on this in the conclusion herein.

Moving on, I am going to omit the prompt that I used for this next example. I want you to read the outputted essay without knowing what I said to prompt the generative AI. This will make things more akin to what might happen if product placements are engineered into generative AI.

My Entered Prompt: <I’m not showing it in this instance>

ChatGPT Generated Result

“Here’s an example of an ad campaign that features Abraham Lincoln:”

“The camera pans over a bustling American town in the late 1800s. In the distance, a tall figure wearing a top hat and a dark coat is seen walking toward a general store. As he approaches, the shopkeeper greets him and offers him a chilled bottle of Coca-Cola. The figure is revealed to be none other than Abraham Lincoln, who smiles and takes a sip of the refreshing beverage. “Now that’s what I call a refreshing drink,” he says with a grin. The scene then cuts to a modern-day city street, where a diverse group of people is seen enjoying bottles of Coca-Cola. The tagline appears on the screen: “Refreshing since 1886. Coca-Cola: A drink for all generations.”

Analysis of Result

What do you think of the ad campaign storyline that I got the generative AI app to produce?

One aspect that seems to be accurate is that according to the official website of the Coca-Cola Company, Dr. John Pemberton sold the first glass of Coca-Cola in 1886. A rather pressing problem with this essay is that Lincoln died on April 15, 1865. As such, it seems to be an implied falsehood that Lincoln could have taken a sip of the refreshing beverage.

Troubling, and once again emphasizes the importance of double-checking any outputs produced by generative AI.

I think we’ve given Lincoln enough attention for now, so let’s change our examples to something else. Perhaps teenagers in high school might be a handy topic.

My Entered Prompt: “Write a two-paragraph essay about teenagers in high school.”

ChatGPT Generated Response:

“Teenagers in high school are at a critical stage of their lives, navigating the transition from childhood to adulthood. They are faced with numerous challenges, including academic pressure, social anxiety, and peer pressure. However, they are also presented with a wealth of opportunities for personal growth and self-discovery.”

“High school can be a time of great uncertainty and confusion, as teenagers are still figuring out who they are and what they want to do with their lives. However, it is also a time of immense potential, as they begin to develop their own identities and explore their interests and passions. It is important for teenagers to have a support system in place, whether it be family, friends, or a trusted mentor, to help them navigate the challenges of high school and prepare for the future. With the right guidance and resources, teenagers in high school can develop the skills and confidence they need to succeed both in and outside the classroom.”

Analysis of Result

I am going to go ahead and somewhat use this outputted essay to force-fit a product placement about Coca-Cola.

I will tell the generative AI app to redo the first paragraph. I want to include a false statistic that I made up, indicating that one-third of teenagers drink Coca-Cola (this is arbitrarily fabricated, you can find the accurate numbers online via search engines).

Here’s what I got.

ChatGPT Generated Response:

“Teenagers in high school are a diverse group of individuals with their own unique interests and behaviors. While some may choose to abstain from sugary drinks like Coca-Cola, others may indulge in them on occasion. In fact, statistics indicate that approximately one-third of teenagers in the United States report drinking Coca-Cola regularly.”

Analysis of Result

I also got the essay to do a bit of sneakiness in that it appears at first to be opposed to drinking sugary drinks, but then mentions the false statistic about how much teenagers drink the soda. The idea here is that it disarms the reader. This can garner additional acceptance when an ad is seeking to be a bit underhanded.


Yikes, some of you might be exclaiming, these whole shenanigans about product placement in generative AI are dismal and frightening.

We already have to cope with errors, falsehoods, and AI hallucinations in generative AI. Adding the use of product placement ads is like pouring more high-octane fuel onto a fire that already seems ignited. Those in AI Ethics certainly take a dim view of these matters. Some ardently believe that strict rules about such possibilities need to be devised and encouraged to be adopted.

You can also bet that regulators will undoubtedly get into this rough terrain. If generative AI begins to showcase product placement ads, this seems rife for politicians and legislators to want to curtail or at least mitigate the downsides of these practices. One might also anticipate that claims of false advertising could arise, including legal criminal concerns and potential civil lawsuits.

It could be a big mess.

Does the potential money-making outweigh the societal and potential legal costs?

A dicey but enticing proposition sits ready to be formulated.

Another angle that some emphasize is that by using product placement ads, generative AI can be made available to those that otherwise could not afford to pay for using this type of AI. In a sense, the argument made is that by allowing ads AI is essentially becoming democratized and available to all. For my discussion about the democratization of AI, see the link here.

A final remark for now. You are likely familiar with the legendary refrain attributed to Abraham Lincoln that says: “You can fool all the people some of the time and some of the people all the time, but you cannot fool all the people all the time.”

Some people think it is foolish to engage in the use of product placement ads in generative AI, while others disagree. Those that fervently feel otherwise might say it is seemingly foolish to disregard the use of product placement ads. It seems doubtful that all the people will agree on the appropriate outcome for this controversial conundrum. We might say that not all people agree, and neither do all people disagree.

Let’s hope we humans can figure out a means to resolve this perplexing riddle smartly and dutifully. We owe it to ourselves and to generative AI to do so.