Tingyu Zhang
Dr. Pullman
February 17, 2025
Week5: Read Is prompt engineering a ‘fad’ hindering AI progress?
Blog about prompting in whatever way you want.
According to AI and Writing by Sidney I. Dobrin, prompt engineering means the process of writing prompts and subsequently adjusting them.  The author is a professor and chair in the English department at the University of Florida in Gainesville. He has written and edited more than 23 books about writing, ecology, and technology.

He mentions there are 5 key points in writing an effective prompt which are being clear, specific, contextual, accurate, and ethical (Dobrin 66). Being clear means the human should type what is intended in the prompts. Otherwise, it may increase the likelihood of hallucinations (Dobrin 66). Being specific refers to having sufficient details to result in a strong output (Dobrin 66). Being contextual is defined as providing as much as background information as possible such as the intended audience and the scenario that the writing is for(a piece of journalism, a brief professional email, etc.), and the intended tone and style(Dobrin 66). Being accurate is due to the fact that Gen AI programs cannot currently discern between correct and incorrect information(Dobrin 66). The inaccurate information used in a prompt also becomes part of the Gen AI’s LLMs, which may poison future outputs from that GenAI program as well (Dobrin 66). Lastly, in terms of being ethical, he argues “ In general, prompts should avoid directing GenAI toward offensive content, intentionally misleading content, and content that might lead to harm. It’s important to keep in mind as well that GenAI programs often exhibit biases and prompts should be written with an awareness of these biases” (Dobrin 66).

Regarding how to refine prompts, Dobrin claims that some strategies can be adopted to revise the initial prompts which do not lead to the outputs the person intends (Dobrin 68). The first one is to clarify details of the task including the purpose, the number of words, the type of sources the individual wishes to use, and their target audience(Dobrin 68). Secondly, people can identify any restrictions. For instance, “avoid the use of first-person language”(Dobrin 68). Thirdly, structure and order the prompt by using a fill-in-blank approach (Dobrin 68). For example, “provide a discussion of 3 key aspects of opportunity cost: 1. ____ 2.____3.____” (Dobrin 68). Fourthly, provide input/output examples to illustrate the style or format the user wishes to receive as an output (Dobrin 68). For example, we might write a prompt with the prefix, “In a voice appropriate to a business workplace, write a report…” or “Writing as if you were a biologist, write a…”(Dobrin 68).

Below is an example of using the regular ones and the Reason Features of ChatGPT, Deepseek, and Perplexity in revising the writing to become more cohesive. My goal is to test which one is the quickest in response and the most excellent in revising their output considering the audience factor.
The first prompt is   “Please revise any mistakes in this writing to be more cohesive and highlight the corrections.”
The second prompt is   “Please revise any mistakes in this writing be more cohesive and highlight the corrections. The reader is a Rhetoric and Composition professor teaching a graduate-level  Writing Research and Methodology course.”
The title of my paper is Integrating Artificial Intelligence into Freshman Composition Pedagogy: Challenges and Solutions for ENGL 1101 and 1102.

I write the introduction part as the situation and overview of the topic. Below is my original text:
“Freshman composition courses, ENGL 1101 and 1102, are required at many U.S. universities, to fulfill core curriculum requirements. These courses help students develop essential writing skills crucial for academic success and career readiness. Through tasks like literacy narratives, visual analyses, argumentative essays, and professional autobiographies, students hone transferable skills such as critical thinking, creativity, and problem-solving. Mastering tasks such as analyzing prompts, generating original ideas, and presenting logical persuasive arguments prepares students to excel in competitive job markets and tackle complex workplace challenges. 
Nowadays, emerging technologies, particularly artificial intelligence (AI), have been increasingly integrated into freshman composition pedagogy. AI, which refers to machines or algorithms capable of performing tasks or solving problems, has seen significant advancements, especially in natural language processing (Hutson et al. 2024). Tools like ChatGPT, Gemini, and CoPilot can understand and generate human language. A report by the Capgemini Research Institute reveals that 70% of American teachers believe curricula and assessments must adapt to AI’s growing influence (Heaton 2024). ”

The result of my testing is below:
Sometimes, the regular CharGPT didn’t follow all of my directions such as not highlighting the words it corrected or even not bolding these words. The regular ChatGPT even hallucinates some of what I’ve written. For instance, ChatGPT suggests I should write”such as” instead of “like” (in formal lists) → “Such as” is preferred in academic writing for listing examples. In reality, I didn’t have “like” in the original sentence of “Freshman composition courses, ENGL 1101 and 1102, are required at many U.S. universities, to fulfill core curriculum requirements. ”

Compared to the regular ChatGPT, Perplexity, and Deepseek, their Reasoning features took longer to generate the outputs but they closely followed my directions by bolding the corrections but the Gen AI could not highlight them. ChatGPT with the Reasoning feature finished the task just in 6 seconds more quickly than Perplexity and Deepseek with the same feature. However, Perplexity and Deepseek with the Reasoning feature can give a simpler and more condensed vision than ChatGPT with the same feature. For instance, in terms of advice on Flow and Cohesion, the Perplexity with Reason feature suggests I remove redundant phrases (e.g., “to fulfill core curriculum requirements” → “core requirements”). Deepseek recommends I replace repetitive phrasing (“required at many U.S. universities, to fulfill core curriculum requirements”) with “core requirements… designed to equip students” to eliminate redundancy and emphasize purpose. Perplexity and Deepseek with the Reason features give similar advice in this sentence.

Considering the prompt with requirement of the audience awareness, ChatGPT with the Reason Feature provided the answer within 16 seconds. Deepseek with the same feature came the second within 25 seconds; Perplexity with the same one did it within 30 seconds. However, ChatGPT with the Reason Feature is the only one without any detailed analysis of the correction and it doesn’t take into account the audience factor as the second version does not change too much.

Overall, Deepseek with the Reason Feature and Perplexity with Feature consider the audience well in their answers by adding more rhetoric and pedagogy terms to the revised prompts. But I cannot tell which one, Deepseek or Perplexity with the Reason Features, is better in giving answers considering the audience.  Although ChatGPT does the quickest job of these 3 Gen AI tools in giving writing revision suggestions,  the regular Chat GPT and ChatGPT with Reason Feature both lack reliability in giving revision suggestions on the original writing.

Here are some screenshots in the testing:

Regular ChatGPT：
Below is the answer to the first prompt: “Please revise any mistakes in this writing to be more cohesive and highlight the corrections.”

Regular Deepseek：
Below is the answer of the first prompt: “Please revise any mistakes in this writing be more cohesive and highlight the corrections.”

Regular Perplexity：
Below is the answer of the first prompt: “Please revise any mistakes in this writing to be more cohesive and highlight the corrections.”

ChatGPT with Reason Feature：
Below is the answer of the second prompt: “Please revise any mistakes in this writing to be more cohesive and highlight the corrections. The reader is a Rhetoric and Composition professor teaching a graduate-level  Writing Research and Methodology course.”

Deepseek with Reason Feature：
Below is the answer of the second prompt: “Please revise any mistakes in this writing to be more cohesive and highlight the corrections. The reader is a Rhetoric and Composition professor teaching a graduate-level  Writing Research and Methodology course.”

Perplexity with Reason Feature：
Below is the answer of the second prompt: “Please revise any mistakes in this writing to be more cohesive and highlight the corrections. The reader is a Rhetoric and Composition professor teaching a graduate-level  Writing Research and Methodology course.”

Works Cited

Dobrin, Sidney I. AI and writing. Broadview Press, 2023.

Tingyu Zhang
Dr. Pullman
ENGL8180 Composition in the era of AI
Look for other explanations of AI in whatever format you like, text, video, infographic. Write a paragraph or two about what you learned and didn’t learn doing this research and then link to what you found, providing a sentence or two gloss for each link.

1.Based on the theory of Selena Sampson Anderson, there are two metaphors about AI: tool or collaborator (47).  According to the author of Generative AI in Writing Education Policy and Pedagogical Implications, Dylan Medina claims in Chapter 4 that we should see AI as a tool instead of a collaborator. What I learned is that AI should be a writing tool for students, because Gen AI is something that writers might engage with and use as part of their writing process (Anderson 47). This tool metaphor gives more agency to the students. Nevertheless, if we regard AI as a collaborator, it may present a challenge to student agency. People have to feed data to create algorithms in Gen AI and LLMs; however, the machine cannot realize their constraints of what is recognizable and what they choose in content generation.Devitt and Nowacek mention one of the main reasons we would study and teach writing or rhetoric is to improve students’ ability to affect the world around them through their rhetorical choices (Anderson 49). Therefore, students should not be taught to “coauthor” with AI since it doesn’t know how to make choices.

What I expected to know but had no clue about this material is how AI can be used as a tool in writing pedagogy and writing class. I believe that we humans should be of greater importance than AI in the writing process and we just need to use AI to give us more ideas and help us find out what our true passion in the topic is, or assist us in figuring out what is a better outline or organization in writing. We should write our ideas first and then use the AI to help us edit them by correcting some grammar or spelling mistakes. Overall, human writers should focus on the content and AI is just a tool for improving our format.

Medina, Dylan. Generative AI in Writing Education: Policy and Pedagogical Implications. Taylor & Francis, 2024.

2. From the online article “What is Artificial Intelligence? Complete Understanding”, I learned the brief history, key terms in AI, and benefits and risks of AI.
Specifically, AI history dates back to ancient times with the idea of creating human-like artificial beings and AI tools; modern AI started in the 1950s.  Early AI web systems were machines that learned from human-fed data and made recommendations based on how they were trained and the algorithms used. For example, Netflix suggests “Escape Room” after you watch “Squid Game.”

Secondly, I understand that Machine learning and deep learning are both key AI concepts, but they differ in scope and approach. Machine learning is a broad field focused on algorithms that help systems learn from data and make predictions or decisions based on patterns. Deep learning, a subset of machine learning, seeks to mimic the human brain’s decision-making process. It specializes in recognizing complex patterns in data and is commonly used in applications like natural language processing, speech recognition, and image recognition.

Lastly, AI enhances business efficiency by reducing human error, improving efficiency and accuracy, and fostering innovation. However, its rapid growth raises concerns about job displacement, biased algorithms, and privacy issues, requiring responsible governance to maximize benefits and address risks.
What I didn’t learn is that the article does not include the relationship between AI and machine learning.

Services Nitor. “What Is Artificial Intelligence? Complete Understanding.” Medium, 14 Feb. 2024, medium.com/@services.nitor1122/what-is-artificial-intelligence-complete-understanding-a0a08ba14935.

Tingyu Zhang
Dr. Pullman
Composition in the era of AI

1.If you are already keeping a commonplace book or digital equivalent, tell us about it. If not, make a list of the subject headings and subheadings you would use to start keeping a commonplace book. Where would you look for content and how would you gather that content? In other words, what would your commonplace practice be.
How did you take notes a few years ago, before ai？

Before AI, I have always used a notebook to keep notes for over 20 years. Specifically, I have used dozens of paper notebook and Word Documents to jot down or type anything important in daily life, school or workplace.

In terms of the process,I would first write down a lot of headings or subheadings at the top of the page such as Composition in the era of AI, Technical writing, Digital Media production, or Life Wisdom. Then I would write down the contents below. I also used many different colored highlighters to categorize, such as pink, orange, green or yellow. To illustrate, I would usually use pink to show what is the most important, orange to show what I could possibly use later, green to show what is totally new for me and yellow to show what I have questions about which I can ask the professors, colleagues or relevant people later.

When it comes to Word Documents, I often took notes of professors’ lectures with some highlighted or underlined words to illustrate the most significant parts. From time to time, I also used a translation tool in class that had both English and Chinese transcripts to help me understand the key points better.
For the content, I used bullet points or numbers to show information in a systematic way.

2. How do you translate (transfer) into the commonplace book?
How are you doing it now with ai?
As I mentioned earlier, I previously used a paper notebook or used Word Documents to take notes randomly.
However, currently with the AI,  I use Goodnotes and Notability to take notes to gather information in class. I tag individual entries with relevant topics, inforamtion types, or sources. Then I also use the highlighted function in the tools.
The difference lies in that I can create certain folders in these apps and insert some pictures of some slides I take in the class presentation. What strikes me is that I can even take notes or highlight some elements in these visual images, which improves my learning efficiency since I don’t need to draw anything by myself and just use the photos I take.
In terms of looking for content, I think the digital note-taking app is easier for the users to make connections between different materials, compared with the paper one. It is because I can use the searching functions and I can store hundreds of different materials just in one device. So I can reduce the anxiety of searching among hundreds of paper. Therefore, I can find some similarities and differences in information. In writing, such connections can lead to inspiration (Pullman).

3. What might you start doing in the bear future?
I might want to try NotebookLM. Notebook LM can take uploaded information and create FAQs, Study Guides, Timelines and Briefing Documents of my reading materials. Best of all, it can also take my uploaded reading materials or notes and create a two-host podcast on the very information I uploaded.
This built-in audio summaries and interactive discussion features can help me digest different reading materials for my literature review, my dissertation or papers in a short period of time.