In our Tuesday readings, we explored a traditional definition for creativity, and Bhatia furthers this by arguing that while AI can produce “artifacts,” it lacks the human capacity for synthesis To me, creativity isn’t just about generating a new sequence of words; it’s about the emotional intent behind them. If there is no “why” behind the work, is it truly creative, or just a sophisticated calculation?

I asked the AI to maintain Silverstein’s iconic rhythm and tone but shift the setting to a sunny day under a shaded tree. Here is the excerpt it produced:

“Today, while lying in the shade, Beneath the tent the branches made, Some Whatifs skipped across the grass And wouldn’t let the quiet pass… Whatif a beetle climbs my knee? Whatif a branch falls off the tree? Whatif the grass begins to prickle? Whatif I sprout a giant pickle?”

On the surface, the output is mediocre at best, as it followed the rhythm instructions perfectly. other than that it looks like it took another shell silverstein poem and swapped a couple of words. Essentially it took a picture of his homework and changed a couple things.

When Silverstein writes about “poison in my cup” or his parents getting divorced, he is tapping into the real anxieties of childhood. The AI, conversely has no experiences to tap into, It’s choosing words that rhyme (prickle/pickle) without any underlying emotional logic. As Bhatia (2025) notes, “AI doesn’t feel tension. It doesn’t labor through ambiguity.” The machine isn’t worried about the future, only predicting the next most likely token in a sequence.

Going into this week, I viewed AI as a powerful collaborator and a way to “reduce processing resources” (UT Aspire) for my technical writing. But this experiment shifted my perspective on the creative side. While I can use a “Physics Professor” persona to fix a lab report, I can’t prompt an AI to have a childhood or feel anxiety.

It has solidified my view that genAI is a calculator for language, not a source of art. It can augment my process by helping me brainstorm structures, but it can never replace the elements that make things human and real that make a poem actually resonate.

Reference: Bhatia, Ashish. “The Artifact Isn’t the Art: Rethinking Creativity in the Age of AI.” Freethink, April 4, 2025. https://www.freethink.com/opinion/studio-ghibli-chatgpt-creativity.

Bad prompting example:

I was using Google Gemini to revise and reformat text for a formal technical report for my Physics 2 Lab

Original prompt: ” remake the abstract, making sure to follow the guidelines listed in the template very strictly.I also need you to add to the conclusion about how our experimental data for 1/r relation did not match the theoretical. be sure to include how the data range of 3 different distances is not very much data. while you’re doing that, go through my PDF and make sure theres no spelling or grammatical errors.”

I also provided it with a draft of an abstract and an example of what a finished abstract looks like

Result: The paragraph returned by the AI did not answer the prompt and complete the task fully. I very clearly asked it to add a part to the conclusion that it fully ignored. It also created a very long conclusion even though I asked it to keep the entire thing short.

Using the UT guide for prompt engineering, I have reworked the prompt to provide me with a much better result.

Reworked prompt:

Why this is improved
The UT paper claims that the AI needs to know who it is, who it is talking to, and why it is doing what is is doing (UT Aspire Prompt Literacy page 2). This new prompt establishes the AI’s identity as an expert, identifies the professor/academic audience , and clearly states the goal of a submission-ready report.

By breaking the request into three numbered, sequential tasks, the number of “processing resources” is reduced and the AI needs to do less logic-based work leading to greater accuracy (UT Aspire Prompt Literacy page 2)
Assigning the AI a specific professional persona helps reduce the likelihood of hallucinations and ensures the language is appropriate (UT Aspire Prompt Literacy page 2)
It tells the AI exactly what to include and what tone to use, preventing broad or general responses (UT Aspire Prompt Literacy page 2)