Chances are, you’ve heard of generative AI and deepfakes by now. Both forms of content can be generated in seconds and are touted as the next big thing for businesses.
But do they live up to the hype? Is human content creation dead for good? Will I need to pack my bags and find a different job?
As a full-time writer myself, I should hate on generative AI and deepfakes. While they’re far from perfect, I believe they serve a purpose.
Let’s dig into the basics of AI-generated content, its pros and cons, and how it’s changing the landscape of content creation.
What is Generative AI?
Artificial intelligence (AI) uses computers to do tasks that traditionally require human intelligence. Virtual assistants like Alexa, the facial recognition that unlocks your phone, and social media ads are all examples of AI in everyday life.
But what about generative AI?
While traditional AI relies on pre-defined patterns to predict outcomes, generative AI uses human input and data to produce an end product. Because of that, you can use generative AI to produce fresh, original content. You can create everything from realistic faces to art to music to code.
And yes, that includes text.
If you plug in the correct prompt, generative AI can create essays, blog posts, website copy, emails, and more.
You give the AI a prompt, it spits text back out, and you continue “chatting” with the AI to revise the copy. When the popular ChatGPT (try it for yourself, it’s free) came out, it almost broke marketing, content creation, and business as we know it.
Let’s play around with it.
Since I’m in the mood for ice cream right now, my prompt will be: “Please write me a sales email about a new flavor of ice cream my business is selling.”
Here’s a snippet from ChatGPT’s output:
“Subject: Introducing Our Mouth-Watering New Ice Cream Flavor!
Dear [Customer],
As a valued member of our community, we are excited to announce the launch of our latest addition to our ice cream range. We’ve been working hard to bring you a new and delicious flavor that will satisfy all your sweet cravings.
Introducing our new [flavor name] ice cream – a tantalizing blend of creamy vanilla, topped with rich [flavor] swirls and chunks of [ingredient]. This delectable creation is a taste sensation that we’re sure you’ll love.
Our [flavor name] ice cream is made with only the finest quality ingredients, locally sourced and churned to perfection by our expert ice cream makers. We’re confident that our newest creation will become a favorite among our loyal customers and attract new ones to our store.”
So, what do you think? It’s not bad, but it’s also not … mind-blowing.
Pros of Generative AI
- Generate ideas and content: Platforms like ChatGPT can help you quickly create outlines and rough drafts.
- Provide a summary of information: When you prompt generative AI, it will search the internet on your behalf and dumps all of the information into a single place.
- Helps with creative tasks: You can ask generative AI to help you come up with cool business names, for example.
- Text can be customized: Adding modifiers to your prompts (“with a fun tone,” “keep this text informative,” “make this text 100 words or less,” etc.) can make your text more unique.
- Saves time: You can generate outlines and rough drafts in seconds, so you have more time to do other things (like eat ice cream).
Cons of Generative AI
- Considered spam: Sorry, folks. AI-generated content is considered spam by Google and other search engines (if published as is). This means your AI-generated emails will be sent straight to the spam folder. If you release AI-generated blogs or web copy, you risk the chance of ranking lower or being completely omitted from search results.
- Possible plagiarism: Generative AI looks to the internet for information, which may result in content that looks very similar to what’s already out there.
- Lacks a human touch: Right now, AI-generated content just doesn’t sound right. It tries to sound human, but it still comes off stiff and too formal. If you create AI content and post it as is, people will know a robot wrote it.
- Factual errors: ChatGPT focuses on creating deceent-sounding content; it doesn’t care if the information it shares is wrong. It pulls information from the murkey depths of the web, which means you need to fact-check AI-generated content for correctness. Even Google’s Bard AI Chatbot made a mess during its debut when it shared a “fact” that was entirely wrong.
- Works better for some things than others: More complex text prompts make the imperfections of generative AI more obvious. If you try to use it for more complex tasks, you’ll have to put in more work editing the content.
What Are Deepfakes?
Deepfakes are a type of AI that uses a technique known as deep learning. Deep learning is AI that imitates how humans gain certain types of knowledge; computers are taught to synthesize information in a way inspired by the human brain.
Deepfakes involve superimposing and manipulating existing media like videos, images, and audio to create new content. Deepfakes can help companies quickly create video content, but they can also be used for evil.
For instance, let’s use Ellie Goulding as a hypothetical example. Ellie Goulding – a known vegetarian who openly talks about her diet – is one day caught on camera eating a steak. There’s a lot of drama, she gets flack for the video, but then the truth comes out. The video was fake.
While deepfakes definitely have the power to be dangerous, they can also save businesses a lot of time and money. You can use tools like Gen-1 to create videos based on a text or image prompt. In an age where companies need to invest more in video but struggle to put in the time to film and edit, deepfakes could save brands a lot of time.
The Pros of Deepfakes
- Enhanced storytelling: Deepfakes offers you the ability to create immersive stories that captivate your target audience.
- Cost-effective: Without a need to pay for sets, props, actors, and other costs, you can make deepfake ad content at a fraction of the cost of traditional video production.
- Shareability: Videos still reign supreme when it comes to social media. Deepfakes make it way easier to create share-worthy videos on your brand’s social feed.
The Cons of Deepfakes
- Ethical concerns: Deepfakes can spread fake news, defame people, and manipulate public opinion. Deepfakes can cause a lot of problems when they’re used for nefarious purposes.
- Trust issues: If a business isn’t transparent about using deepfakes, it can erode customer trust. If it’s bad enough, this could hurt your company image and even lose you customers.
- Legal implications: When misused, deepfake technology can infringe on laws related to intellectual property, privacy, and defamation. Yikes.
AI and the Future of Content Creation
Whether we like it or not, generative AI and deepfakes are changing the way we create content.
Generative AI helps marketers and businesses save time, but it’s still considered spam and lacks that conversational, authentic human voice. Deepfakes make it super easy for businesses to create videos, but they come with a gambit of legal and ethical risks.
It’s hard to predict where AI-powered content will take us, but it’s clear that humans will always play a critical role in the content generation process. If you need human-centered copy that’s different from the “bleh” AI copy your competitors are writing, use a human writer. AI content is okay, but I’m passionate and pretty darn good at what I do. You get better results when your brand sounds human, and AI just isn’t there yet. If you feel overwhelmed at the thought of writing copy, professional marketing writers like yours truly are always here to help.