Everything that we have covered in this class has been under the assumption that the integration of AI into daily tasks is inevitable. I wish that I did not agree with this fact, but I do. I spend many hours of my life on Adobe platforms, and I have for many years. One thing that I have noticed the most is that with every update of Adobe comes another AI tool that is shoved into your workspace. It has gotten to the point that after working in Photoshop for too long, my computer will start to crash.

While this is extremely frustrating, I have also found that many of these AI tools do help me to complete simple tasks faster. Just as we have discussed in this class, AI is never perfect and even when I am using it on a platform that is suggesting its use, I often have to go back through and fine tune the changes that AI made to any given project. This use of AI tools is not going to go away in the content creation realm any time soon. At first, it seemed like the AI tools were something fun to just play around with, but now it seems as though I cannot complete a project without using them at least once.

From this class, I have gained the knowledge to ethically pick and choose my moment of using AI. LLMs are never going to replace human creativity, but they have made it easier to navigate creative outlets that have often been too complicated for an untrained eye. In the future, I hope to continue to use LLMs and their tools to further my work and polish designs. But I never want an LLM to determine what my pieces convey or change my style.

This week’s readings tackled an issue that we all have been facing in the academic world. Dinsmore and Fryer (2026) brought forth many issues that arise when students bypass the struggle of learning new content by asking LLMs for summaries. It was surprising to me that summarizing is actually an important part of the learning process and accumulating information into our current schemas. During the NotebookLM portion of class, when asked to summarize our sources, NotebookLM referenced this “illusion of mastery,” or the belief that because one read an LLM summary of the content, one understands it. According to Dinsmore and Fryer, this is not the case, as one never went through the process of comprehending the material.

LLM companies harvesting data is concerning and an issue that needs to be brought to the forefront more. It is worrisome that you make the effort to remove your data from their systems. I believe that the more and more we mention these issues, the more and more pressure we put on these large companies to change their privacy policies. After these readings and experiments, I am making more of a conscious effort to remove data I do not want to share with the world from ALL LLMs that I have used.

Dinsmore, Dan L., and Luke K Fryer. “What Does Current genAI Actually Mean for Student Learning?” Elsevier, 2026, www.sciencedirect.com/journal/learning-and-individual-differences.

During the lab in class on Tuesday, my group asked different LLMs to write poems in the style of Shel Silverstein. When I first prompted Gemini by saying, “Write a poem in the style of Shel Silverstein.” At first, Gemini just gave me a poem written by Silverstein himself, which seemed to go against copyright in my brain.

Later in the experiment, I prompted Gemini to “Write a poem similar to Silverstein’s poem Rain.” Gemini gave me back this poem:

The Cloud’s Big Sneeze

I opened my mouth to catch a drop, And prayed the sky would never stop. It tickled my chin and it wet my nose, And soaked the socks inside my shoes (and toes).

My umbrella turned inside out like a cup, To catch all the sprinkles that didn’t stay up. The worms are out dancing, the grass is a lake, And I’m shivering here for goodness’ sake!

The sky caught a cold, or so it would please, To give us a giant, wet, watery sneeze. So I’ll sit in this puddle and wait for the sun, ‘Til the clouds are all empty and raining is done.

This poem is by no means creative. While I understand that the definition includes novelty and usefulness, it is extremely sparse and does not offer limitations; it does suggest that for something to be considered creative, it must be new. I partly agree with this idea. I think the most creative solutions consider differing perspectives and look at the world in ways that the traditional problem solver might not. Some may say that “all great artists steal,” that there are no longer any unique ideas, and that the idea of creativity has changed as we have all just become proficient thieves. In this regard, Gemini’s poem would be creative, but there is a difference between being inspired by another person and just changing their words, while keeping the idea the same. I believe that because the LLM did not produce a new idea but just reworked someone else’s poem, it is not creative.

Based on the output that Gemini gave me, I have changed the way that I would use AI in the creative process. I often use AI as a brainstorming or an idea-hatching ground. I give the LLM where I want to go, and ask it to create different launching grounds. Now that I know that LLMs do not create new ideas or even suggest unique ones, but rather, they just spit out another person’s ideas worded differently. Now that I know this, I know that I need to change my ideas to further stray away from any launch pad that AI may create for me,

“The Artifact Isn’t the Art: Rethinking Creativity in the Age of Ai.” Freethink, 7 Apr. 2025, www.freethink.com/opinion/studio-ghibli-chatgpt-creativity?utm_source=tldrai.

The most useful prompt guideline that I found was the persona pattern. When I first prompted ChatGPT to “Write me a swim set.” I kept it very bland, and in return, I received a response that was just as bland and simple as what I inputted.

What I received was not what I was looking for and did not match what I had expected. In the following prompt, I assigned Chat the role of being my swim coach and informed it of my history of swimming.

After assigning Chat a role, it was able to write me a much more specific and well-rounded workout to match a Wooster swimmer’s level. Additionally, when prompting Chat the second time around, I gave it specific goals, which seemed to help eliminate the guessing work that Chat was attempting to complete.

Based on what I have learned in this experiment, I can at least confidently say that when asking Chat to create a regimen of some sort, both assigning it a role as well as limits is helpful. Just as stated in the prompting guides, LLMs just predict what you want and offer broad responses, so if you are extremely specific in your ends, you are more likely to meet them (UT Guide). The main thing stated in the UT Guide is that keeping your end goal clear is the most important part of prompting. By assigning Chat a role and setting limits, I was able to match UT’s guide and get an outcome that was much more to my expectations. This can be helpful in the future if I have a specific means and an idea of a product, where I can set limits and expectations while prompting Chat.

When comparing ChatGPT and Notebook LM’s abilities to act as a research assistant on racial bias in AI facial recognition software, it became evident that Notebook LM offered a lot more detailed and relevant information than Chat did.

My prompt for Chat was: “Act as a research assistant for me. Researching racial bias within AI facial recognition software using language friendly for college students.” This resulted in many different subsections, all of which contained two or three bullet points that contained brief headings of more that could be found. Some of these subsections included current “solutions” to the bias problem, the “Gender Shades” study mentioned in class, and explained how Ai became biased, blaming training professionals as being biased themselves.

After importing the same sources pulled from ChatGPT into Notebook LM, I then asked Notebook: “Search sources for the reason for the bias in facial recognition software.” Notebook LM provided a lot more detail and was able to reference specific sections within the sources that provided statistics of bias in facial recognition. However, Notebook LM also has a section that places part of the Ai bias on the trainers and the data provided, stating that Ai is not a perfect tool.

Based on these findings, I can gather that Notebook LM would be more useful when writing a research paper and when it comes to creating in-text citations. Nonetheless, based on what both Chat and Notebook provided me, I can safely say that it is not a good choice for police to use Ai facial recognition in investigations, as there is still much training to be done to shrink the size of bias within these systems.

Sources:

National Institute of Standards and Technology (NIST). (n.d.). Demographic Effects in Face Recognition. Retrieved from https://pages.nist.gov/frvt/reports/demographic/

• Buolamwini, J., & Gebru, T. (2018). Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification. Proceedings of Machine Learning Research, 81, 1–15. Conference on Fairness, Accountability, and Transparency.

Sarridis, I., Koutlis, C., Papadopoulos, S., & Diou, C. (2025). VB-Mitigator: An Open-source Framework for Evaluating and Advancing Visual Bias Mitigation. AEQUITAS 2025: Workshop on Fairness and Bias in AI

Hello! I am Genevieve McCullar, and I am a freshman from Elizabeth, Colorado. I am on the swim team and absolutely love to do anything outside, especially if it is on a lake.