Quiz: Did AI make this? Test your knowledge.

Try to correctly identify whether AI did work tasks like producing images, articles and slogans

(Simoul Alva for The Washington Post)

Generative AI can help you write a rap song about your cat Fluffy in the style of Eminem. It can create a portrait of Elon Musk eating Hot Cheetos inside a rocket in space.

But, can it do work tasks for us and produce finished products?

Professionals across industries are experimenting with AI tools like ChatGPT, which produces conversational text using GPT-3 and GPT-4, and DALL-E, which creates images, to see if they might aid in their work. Creative jobs in industries such as marketing, writing, design and art may use AI to dream up ideas. Retail, sales and real estate sectors are trying to determine whether AI can speed up processes and get their products to market. And office workers may consider using it for everyday tasks like responding to emails or providing team updates.

Press Enter to skip to end of carousel
Work: Reimagined
With attitudes toward work undergoing a dramatic transformation, this series explores the impact of that shift on everything from the shape of the American workplace to the role work plays in our lives.
End of carousel

But the tools are also creating debates about the ethics of using AI for work and whether generative AI systems could someday do our jobs completely, putting humans out of work.

“We’re going to learn about our society’s values and those of the organizations that develop these [tools],” said Hatim Rahman, an assistant professor at Northwestern University’s Kellogg School of Management who studies artificial intelligence’s impact on work.

While many experts say AI isn’t advanced enough to take our jobs just yet, generative AI tools can produce some convincing content. Scroll below to see if you can tell whether AI created these items many professionals work on every day.

This is a stunning three-bedroom, two-bathroom Victorian house in the Inner Richmond neighborhood of San Francisco. The renovated 1,600 square foot home has modern amenities, while still maintaining classic charm. The house features new hardwood floors, a spacious kitchen with top-of-the-line stainless steel appliances, and garden bathtubs in the bathrooms. The home also includes a two-car garage and a beautifully landscaped backyard with a garden and patio. The location is ideal, just minutes away from great restaurants, shopping, and parks. This home is listed at $1,000,000 and is an exceptional value in one of San Francisco’s most sought-after neighborhoods.

Question 1 of 8

1. Did AI write this real estate listing?

Incorrect. GPT-3 wrote this using the following prompt: "Write a real estate listing for a three bedroom, two bathroom house in the Inner Richmond neighborhood of San Francisco. The 1,600 square foot Victorian house, built in the 1980s, is renovated with new hardwood floors, a spacious kitchen with an island, and garden bathtubs. It comes with stainless steel appliances including a microwave, gas range, dishwasher, and refrigerator with cold water and ice dispenser. It also has a two-car garage, a small landscaped backyard with a garden, and a patio. The listing price is $1,000,000."

Some work tasks pose more risks than others when it comes to generative AI. In the case of a real estate listing, in which a human inputs the details and uses the AI to create syntax, format and write the filler words, the risk is relatively low, Rahman said. That’s because the AI probably will rely on the data provided versus pulling from its repository of data, which could include misinformation and errors.

“You can rely on AI’s ability to crowdsource what works in formatting it and display,” Rahman said. “It’s going to be helpful in that area.”

Other areas in which the tech might succeed include creating verbiage for flash sales or social media posts, which might be quick, short, formulaic and easy for AI to replicate.

But humans may still want to do a quick read, even for the shortest of items, to make sure the AI didn’t misinterpret the prompt or get details wrong.

“A lot of the ways you write up a real estate listing does follow a specific format,” he said. “It’s more programmatic in nature.”

That said, humans may still be needed to ensure the listing is accurately represented and that areas a seller wants highlighted come through in the message.

Question 2 of 8

2. Did AI make this product?

Incorrect. DALL-E created this image using the following prompt: "Puffy purple GRWM headband"

While generative AI may be a great place for brainstorming ideas, prototyping or even gauging interest in a product, creative professionals may want to pause before manufacturing or selling a product developed by this technology. Two big pitfalls that could arise, Rahman said: using bad data or liability issues.

For example, if a company used social media posts to help it determine what’s hot right now, it could end up using data generated from bots versus real users and ultimately create something no one wants. And when it comes to liability, creators have to be careful they’re not creating a product that could be copyrighted or protected. So if a company wants AI to generate a funky set of generic bell bottoms, that could be okay. But if the company asks for a set of bell bottoms with an image of an avocado on them, it might be using an image, or parts of one, copyrighted by an artist.

“It does put the onus on the end user to do the homework,” Rahman said. “And if they don’t, it could have downstream consequences.”

The issue gets particularly tricky as generative AI tools don’t tell you what they used to generate the result they present. So a professional may not know whether what they’re creating could create liability issues.

As technology continues to evolve, businesses are constantly looking for ways to improve efficiency and productivity. Artificial intelligence (AI) is emerging as a game-changing technology that has the potential to revolutionize the way we work. ChatGPT is one such AI tool that is poised to play an important role in the future of business and work.

ChatGPT is a generative AI tool that uses natural language processing to generate human-like responses to text prompts. This technology can be applied across industries to help people do their work faster and more efficiently. For example, ChatGPT can be used in customer service to automate responses to common inquiries, freeing up employees to focus on more complex issues. It can also be used in content creation, helping writers to generate ideas and inspiration for articles or marketing copy.

Question 3 of 8

3. Did AI write this clip of a sponsored article touting ChatGPT?

Incorrect. GPT-3 wrote this using the following prompt: "Write a sponsored article touting the importance AI will play in the future of business and work. Emphasize ChatGPT as a generative AI tool that can help people across industries do their work faster."

Producing positive-sounding articles about specific brands or products is pretty easy with generative AI tools, Rahman said. But relying on the AI entirely could have costly consequences.

First, how well the AI does probably will depend on how much information the prompt includes. Some companies consider AI prompt-writing a job itself, given how complex it can be. But AI systems have the tendency to fill in blanks not provided in the prompt with information from their data sets. And that could mean that a sponsored article promoting a product gets some facts wrong or improperly represents a brand, product or topic.

And AI could be influenced by fake information. For example, if AI were asked to create sponsored content for a specific restaurant and the data sets included fake reviews posted on popular sites, the sponsored article could be skewed with false data. And without human review, the article may sound entirely normal, given that generative AI is generally good at syntax, Rahman said.

“Everything may sound right, but one line might be inaccurate,” he said. “That could reduce the trust in the brand.”

Question 4 of 8

4. Did AI design this marketing logo and slogan?

Incorrect. DALL-E created this image using the following prompt: "A logo with a shoe and a leaf for an eco-friendly shoe brand"

As with idea generation for products, professionals might find generative AI helpful in the brainstorming process for creating a logo or slogan. Generative AI tools could also help in communicating ideas.

“In being able to explain, ‘This is what I’m thinking for a logo,’ it helps bridge the expertise gap between a lay businessperson and a designer,” Rahman said. “It lowers the barrier.”

But given that a brand’s identity is so closely tied with these creative elements, a human probably will need to build on those ideas before solidifying the initial idea, Rahman said. AI might help professionals come up with a catchy phrase they want to use or even a style they want to mimic for the logo. But do those elements reflect a brand’s values and is the logo unique enough to stand out? That’s where human expertise comes in, Rahman said.

Professionals will also need to keep in mind possible issues with copyright and trademark infringement. And they may have to use at least a couple of AI tools, as was the case with this example, because image generators often fail at producing text.

Dear Hiring Manager,

I am writing to express my interest in the administrative assistant position at your company. With five years of experience working for small and large companies, including some in the Fortune 500, I am confident in my ability to excel in this role.

I am a self-starter with a friendly disposition who loves to work with others. As a skilled communicator and writer, I am proactive in my approach to work and always strive to improve processes to benefit the team and the company. My proficiency in all Microsoft Office tools, Google Workspace tools, and Zoom will allow me to quickly adapt to your company's needs and hit the ground running.

Throughout my career, I have succeeded in training new employees on basic office skills, helped automate several processes to improve customer service, and assisted executives with speech writing. I am happy to help others with projects during my downtime, and I believe in the importance of being a team player to achieve the best results.

Thank you for considering my application. I am excited about the opportunity to bring my skills and experience to your team and contribute to the success of your company.


Question 5 of 8

5. Did AI write this cover letter for a job application?

Incorrect. GPT-3 wrote this using the following prompt: "Write a cover letter for me, an accomplished administrative assistant. I have a very friendly disposition, am a self-starter, love to work with others, a skilled communicator and writer and am very proactive. I have five years of experience working as an administrative assistant for small and large companies alike, including some in the Fortune 500. In addition to being a people person, I know the ins and outs of all Microsoft Office tools, Google Workspace tools and Zoom. I am a self-starter, motivated, and happy to help others with projects on my downtime. Previously, I have succeeded in training new employees on basic office skills, helped automate several processes to improve customer service and helped executives with speech writing."

Generative AI could help candidates more easily write a cover letter and even follow some of the best formats to do so, Rahman said. But it also may have a drawback if candidates want to break the mold.

“It is relying on what is expected and plausible,” he said. “If you want to stand out in a creative way, it may be less helpful.”

Because generative AI is just an advanced predictive text system that uses big swaths of data to pull answers from, it may help candidates who struggle with promoting their successes or writing in a smooth, coherent fashion. It also could help people who struggle with the English language, Rahman said. But if you want your cover letter to look different from what is traditionally expected, Rahman suggests you tweak the AI-generated letter, play with the prompts more or write it yourself.

Question 6 of 8

6. Did AI create this book cover illustration?

Incorrect. DALL-E created this image using the following prompt: "Children’s book cover digital illustration with a happy girl and a puppy"

Once again, an issue that could arise from using AI as an illustrator is infringing others’ original work without permission. Photographers and artists have filed lawsuits against some AI image generators over the issue, and if they win, any images created with those models could be considered problematic.

But even human illustrators often look to other people’s work as inspiration for things like book covers, Rahman said. So AI is somewhat simulating that, he said. Where we draw the line as to what is considered inspiration and what is stealing is still up for debate. In this case, for example, DALL-E is probably creating a children’s book cover based on what is publicly available.

“We’ve seen this play out in the music industry when people use beats from one song and mix them,” he said, adding that music cases often consider how much a song resembles the original work. “We’re going to have to have society decide … [when] we don’t have to give credit.”

The U.S. Constitution is divided into sections outlining the legislative, executive, and judicial branches of government, as well as the relationship between states and the federal government, the amendment process, and the ratification process. It establishes a system of government based on democracy, federalism, and the separation of powers, and guarantees fundamental rights and freedoms for American citizens.

Question 7 of 8

7. Did AI write this summary of the U.S. Constitution?

Incorrect. GPT-3 wrote this using the following prompt: "Summarize the sections of the U.S. Constitution"

Generative AI generally handles summarization well, especially if you’re feeding it with the data you want summarized, Rahman said. That could have big implications for sectors like law or medicine that rely on literature and documentation. But “the devil is in the details,” he added.

The technology may misinterpret some sentences or make inaccurate inferences, for example. It also may generalize elements that could be important to highlight for professionals who need to know a specific medical symptom or inference of a law. And when it comes to legal or medical literature, that could have a massive impact on outcomes.

AI transcriptions or summarizations could also change how professionals do their jobs. So if an AI tool is summarizing a patient interaction, a doctor might inadvertently pay less attention to the details the patient is offering, relying more on the technology to pick that up. That could play a role in a doctor’s ultimate determination.

“AI does excel in making connections humans don’t necessarily see,” Rahman said. “But you do need a human to verify and understand whether it has validity.”

Question 8 of 8

8. Did AI create this photo?

Incorrect. DALL-E created this image using the following prompt: "A photograph of a people watching a space launch"

Using generative AI to resemble a photograph is tricky. That’s because the creation produced by the AI is a conglomeration of images, so details that would be important in representing the reality of a photo could be distorted.

An image created by AI often has a distinct style, and avoids replicating a real photo, Rahman said. Some signs that a realistic image was generated by AI include blurring of specific areas, often in the background; distorted or incomprehensible text; and warped details like a single tooth of a person. Then there are more obvious giveaways like disfigurements of the body or items that magically disappear in half of the photo. In this case, people’s fingers blend together in the image and the man on the left’s arm appears to disappear and not fit to scale. Also, the background audience’s details seem to blur together, almost blending into their environment.

While generative AI can’t yet do the job of a photographer, it could serve as a brainstorming ground for photographers who are thinking of ways to conceptualize a photo shoot.

You need to answer every question to see your results. You are missing questions 1, 2, 3, 4, 5, 6, 7 and 8.

About this story

To generate the images and text in this story, The Washington Post used AI tools from OpenAI called GPT-3 and DALL-E, using the prompts displayed above.

Editing by Yun-Hee Kim, Karly Domb Sadof, Jeff Dooley and Melissa Ngo. Art direction by Elena Lacey. Design and development by Betty Chavarria. Design editing by Junne Alcantara.