The explosive popularity of AI can be traced back to early last summer as Craiyon, an AI model formerly known as DALL-E mini, seemingly took the internet by storm. With the ability to transform almost any text prompt into a generated image, users of the site were eager to share their creations on social media platforms such as YouTube, Twitter, and Instagram. As 2022 progressed, so did the quality of art generating AI, with Midjourney and Stable Diffusion becoming the most impressive and popular models. This year, though, attention is being put onto ‘chatbots,’ an AI model capable of authoring basically anything.

The most popular chatbot is ChatGPT. An advanced language model developed by OpenAI, ChatGPT generates text based upon user prompts. Suggested prompts on the official ChatGPT website include, “Explain quantum computing in simple terms,” “Creative ideas for a 10 year old’s birthday,” and “How do I make an HTTP request in Javascript,” but the chatbot is capable of much more. 

To test its abilities, Andrew Gray, the current website editor for the Grizzly Growl, was asked to give ChatGPT several prompts. Here are some of the results:

Q: How would you best describe the current state of the world?
A:The current state of the world can be described as dynamic and constantly evolving, with various challenges and opportunities in different domains such as politics, economics, health, and technology. There are ongoing issues such as the COVID-19 pandemic, economic inequality, and geopolitical tensions, as well as progress in areas such as renewable energy, vaccine rollouts, and remote work solutions.

Q: What is the best way to train a dog?

A: The best way to train a dog is to use positive reinforcement methods, such as rewards and praise, to encourage desired behaviors. Consistency and patience are key in dog training, as well as clearly communicating commands and boundaries. Training should be tailored to the individual dog and can involve obedience training, socialization, and behavior modification as needed. It may also be helpful to seek the guidance of a professional dog trainer or behaviorist.

Q: Tell me a story about a Goblin who lives inside of a high school
A: Once upon a time, there was a mischievous goblin named Grum who lived inside a high school. Grum was small, green, and had a wide, toothless grin. He loved playing pranks on the students and teachers, causing all sorts of chaos and mayhem throughout the building.

Despite his mischievous ways, Grum was very good at hiding and staying out of sight. He lived in the walls of the school, popping out only when no one was around to cause his latest mischief. The students and teachers whispered about the strange noises and disappearances that happened in the school, but no one could ever find the source of the trouble.

One day, a new student named Lily arrived at the school. Lily was a curious and adventurous girl, and she was determined to figure out what was causing the strange happenings in the building. With her sharp mind and fearless spirit, Lily quickly realized that Grum was the source of the trouble.

Lily decided to make friends with Grum, instead of turning him in to the authorities. Grum was wary at first, but Lily’s kind and persistent nature won him over. The two of them had all sorts of wild adventures inside the walls of the school, with Lily always managing to keep Grum’s pranks under control.

Years passed, and Lily graduated from the school. She left Grum behind, but she promised to come back and visit. And every now and then, when the students and teachers at the school hear strange noises or experience unexplained disappearances, they smile, knowing that Grum is still there, causing his mischievous mayhem. And they remember Lily, who showed Grum that even a mischievous goblin could have a friend.

Based on these responses, you may be impressed by the chatbot, but ChatGPT isn’t just capable of answering quick questions and telling stories. Business Insider recently published an article compiling a list of several exams, tests, and assignments that the chatbot has been able to pass. This list included business exams, the US medical licensing exam, and four law school exams. The professors interviewed bring up that, although not perfect, “Its performance was sufficient to successfully earn a JD degree from a highly selective law school, assuming its work remained constant throughout law school (and ignoring other graduation requirements that involve different skills). In an era where remote exam administration has become the norm, this could hypothetically result in a struggling law student using ChatGPT to earn a JD that does not reflect her abilities or readiness to practice law.”

Naturally, students are already living up to this fear. In another recent article, this time from the New York Post, an assistant philosophy professor discusses catching a student using ChatGPT for their work. “It writes like a very smart 12th-grader,” claims Darren Hick, but he also warns that it won’t always be so noticeable, “This is learning software — in a month, it’ll be smarter. In a year, it’ll be smarter. I feel the mix myself between abject terror and what this is going to mean for my day-to-day job — but it’s also fascinating, it’s endlessly fascinating.” Due to the fact that unless the AI takes specific parts from other articles, plagiarism checks don’t work on chatbots, making it an almost completely foolproof way for students to cheat on their work.

Due to this concern, schools across America, including the Jordan School District, have taken to blocking and banning the use of ChatGPT in schools. This supposed solution, however, is easily worked around. Ever since the Covid-19 pandemic, schools have shifted their focus towards more online learning and teaching. Almost every assignment that students are given is being turned in online. Due to this, students can still access ChatGPT from their homes or even their phones as long as students are using cell data or have a VPN.

Shortly after public schools in New York City and Seattle banned the use of chatbots in the first weeks of January 2023, Kevin Roose published an article for the New York Times titled, “Don’t Ban ChatGPT in Schools. Teach With It.” In this article, he advocates for the embracement of this new technology. For the short term, he states that, “Schools should treat ChatGPT the way they treat calculators — allowing it for some assignments, but not others, and assuming that unless students are being supervised in person with their devices stashed away, they’re probably using one.” Then, in coming years, he suggests that schools should reemphasize in-school tests and discussions in favor of take-home assignments. Compounded with the fact that AI chatbots are certainly here to stay, a better understanding of chatbots is going to better prepare students for the world they’ll go on to live and work in.

Regardless of what you believe about AI chatbots, a future involving them is guaranteed. The potential for this technology is already enormous and it will continue to impact the way we write forever. At the same time, it’s completely rational to be wary of a tool that could be used by lazy students in order to skip doing their work. Improper handling of these AI models in schools will certainly become a major issue in the future for our society, which is why it’s now more important than ever to adapt to the technology of our time.