{"id":1096,"date":"2024-12-10T22:57:50","date_gmt":"2024-12-11T03:57:50","guid":{"rendered":"https:\/\/pressbooks.bccampus.ca\/communicating\/?post_type=chapter&p=1096"},"modified":"2026-02-14T13:35:27","modified_gmt":"2026-02-14T18:35:27","slug":"chapter-15","status":"publish","type":"chapter","link":"https:\/\/pressbooks.bccampus.ca\/communicating\/chapter\/chapter-15\/","title":{"raw":"Writing with Generative AI","rendered":"Writing with Generative AI"},"content":{"raw":"ChatGPT, while advanced and capable of generating coherent and contextually relevant text, still has several limitations that make it inferior to authentic human writing. Here are some key ways in which ChatGPT falls short:\r\n
    \r\n \t
  1. Lack of True Understanding<\/strong>: ChatGPT doesn\u2019t truly understand the text it generates. It lacks genuine comprehension and is simply predicting what words and phrases are likely to come next based on patterns in the data it was trained on. Humans possess deep understanding, emotions, and the ability to connect ideas in a nuanced and meaningful way.<\/li>\r\n \t
  2. No Personal Experience or Creativity<\/strong>: ChatGPT lacks personal experiences, emotions, and creativity that humans bring to their writing. It doesn\u2019t have genuine thoughts, feelings, or unique perspectives to draw from.<\/li>\r\n \t
  3. Limited Contextual Awareness<\/strong>: While ChatGPT can maintain a short-term context in a conversation, it can struggle with maintaining a deep, nuanced understanding of long conversations or intricate topics. It may sometimes provide responses that sound relevant, but are contextually incorrect or inappropriate.<\/li>\r\n \t
  4. Inaccurate Information and Biases<\/strong>: ChatGPT can generate inaccurate or outdated information since its responses are based on the data it was trained on. Additionally, if the training data contains biases, the model might inadvertently generate biased or prejudiced content.<\/li>\r\n \t
  5. Unsatisfactory Flow and Coherence<\/strong>: Although ChatGPT can produce coherent sentences, it sometimes struggles with maintaining a natural flow of thought, resulting in responses that may seem stilted or disjointed compared to human writing.<\/li>\r\n \t
  6. Limited World Knowledge and Creativity<\/strong>: ChatGPT\u2019s knowledge is limited to what it was trained on up until September, 2021. It lacks access to new information and developments that have occurred since then. Moreover, while it can mimic creativity to some extent, its creative output is often based on patterns in the training data, rather than genuine imagination.<\/li>\r\n \t
  7. Empathy and Emotional Depth<\/strong>: Humans can infuse their writing with genuine empathy, emotional depth, and understanding of the human experience. ChatGPT lacks true emotions and can\u2019t empathize in the same way.<\/li>\r\n \t
  8. Subjective and Aesthetic Judgments<\/strong>: Humans can make subjective judgments about aesthetics, art, beauty, and emotions that go beyond the scope of ChatGPT\u2019s capabilities.<\/li>\r\n \t
  9. Adaptation to Individual Styles<\/strong>: Humans can adapt their writing to various styles, tones, and preferences of the intended audience. ChatGPT\u2019s style may sometimes be inconsistent or not align well with specific audiences.<\/li>\r\n \t
  10. Errors and Misinterpretations<\/strong>: While humans can often catch errors, ambiguities, or misunderstandings in their writing, ChatGPT can generate responses that are grammatically incorrect, factually wrong, or contextually inappropriate without realizing it.<\/li>\r\n \t
  11. Dynamic and Evolving Responses<\/strong>: Humans can engage in dynamic, evolving conversations, responding to changing contexts and adjusting their responses accordingly. ChatGPT may struggle to adapt to rapidly shifting conversational dynamics.<\/li>\r\n<\/ol>\r\nIn summary, while ChatGPT is a powerful tool for generating text and assisting with various tasks, it lacks the depth, authenticity, understanding, and genuine creativity that humans bring to their writing. It\u2019s important to recognize its limitations and use it as a complement to, rather than a replacement for, authentic human writing.\r\n\r\n
    \r\n\r\nEverything above that line was written by ChatGPT in response to this prompt: \u201cIn what ways is ChatGPT inferior to authentic human writing?\u201d The only edits above were to correct for punctuation errors (yes, ChatGPT messes up its punctuation sometimes).\r\n\r\nSo, if those are the problems, how can ChatGPT help professional communicators produce quality content?\r\n

    Brainstorming<\/h3>\r\nThere\u2019s nothing I particularly disagree with up there and I doubt I would have thought of all those problems with ChatGPT on my own (though it was a bit repetitive at times).\r\n\r\nThat\u2019s the first hint about writing with ChatGPT. It\u2019s good at gathering a range of ideas that you might not have thought of all by yourself. ChatGPT is good at brainstorming.\r\n\r\nThe pressure to constantly dream up new content can be frustrating, especially as you get the feeling that you have already created similar content in the past. ChatGPT can help you come up with some new content ideas.\r\n

    Outlining<\/h3>\r\nSimilar to brainstorming, ChatGPT will suggest an order for how information should be provided. It might need to be corrected, but it\u2019s a starting point for how to organize your longer content, such as a blog article. When creating outlines, it sometimes has problems in its organization and hierarchy; information that should be a subsection is presented as a major section and information that should be a major section is presented as a subsection. Also, content can easily be replicated across more than one section (ChatGPT has lousy memory).\r\n

    Speed<\/h3>\r\nEven the most prolific writers with the quickest fingers in the planet would be hard pressed to produce quality original content at faster than 50 words per minute. (Yes, folks can type faster, but as they do, their ability to focus on quality content goes down.)\r\n\r\nOn the other hand, ChatGPT can produce about 400 words of passable\u2014though rarely great\u2014content in a few seconds. But there\u2019s the problem again: a large amount of quickly available text is only good if the text is good; it\u2019s mostly in the range of \u201cokay.\u201d\r\n\r\nWhat does that mean for professional writers? ChatGPT can increase the speed of producing draft paragraphs. As noted above, ChatGPT loses the plot after a while, so you can\u2019t use it to produce a first draft of a long document, but you can use it to produce a few paragraphs, or perhaps one contained section, as seen above.\r\n\r\nGiven the problems, you\u2019ll need to re-write those paragraphs to inject emotion and examples. If stating information that needs to be cited, you'll need to verify the accuracy of the information, correct as necessary, and cite an authority for the relevant information. ChatGPT cannot be trusted to be factual or accurate. You\u2019ll need to make sure there\u2019s continuity from one section to the next. But you\u2019ll have a bit of draft material to work with more quickly.\r\n

    Availability<\/h3>\r\nYour generative-AI writing assistant never sleeps and never takes a day off. We mortal humans, on the other hand, need sleep and days off. Without that, our writing quality gets worse and worse.\r\n

    Appropriateness<\/h3>\r\nAs a follow-up to the previous paragraph, ChatGPT never talks trash or drunk posts. The program is less likely to make embarrassing typos from fatigue or intoxication. For example, how easily can you post about your organization\u2019s pubic places, instead of its public<\/em>\u00a0places? Oops for you, but that\u2019s a mistake ChatGPT is unlikely to make.\r\n\r\nA mistake ChatGPT will sometimes make, though, is to produce content that is politically problematic, such as reinforcing negative, sexist, or racist stereotypes. That must be accounted for and corrected.\r\n

    Enhancing Vocabulary<\/h3>\r\nIn the same way that ChatGPT can help with brainstorming, it can help with rephrasing and vocabulary. The program can be asked to explain something better or with new word choices. In this way, it\u2019s like a thinking thesaurus.\r\n

    Role Playing<\/h3>\r\nIf you\u2019re wondering how your audience might respond to a post, try asking ChatGPT. Ask the program how a well-defined audience (give some demographic and other information about the audience) would respond to content you\u2019ve drafted. Try it out with a few different target audiences. Let this help you anticipate how people might engage with your content. Revise to get the results you want and see what happens.\r\n

    And Now, Words of Caution<\/h2>\r\nYes, ChatGPT (and competing products) is great, but never outsource your critical thinking. Students are well advised to do their own brainstorming and outlining before<\/em> they consult ChatGPT. Going to ChatGPT first undermines your own ability to produce better results because your brain will get lazy when it has a quick, simple, relatively good option made available.\r\n\r\nTo illustrate this point, let me share a story. A former student of mine asked me for a reference letter (this happens often enough when you teach at a college\/university). As always, my response was this: \"sure, but please write me the first draft of what you want in your reference letter.\" She promptly went to ChatGPT and sent me the content on the left. Because I cared about her and was willing to forgive this lazy approach for a special student, I produced the version on the right. Take a look at the differences and note where a human voice offers an improved written product.\r\n\r\n\r\n\r\n
    \r\n

    ChatGPT version<\/strong><\/span><\/p>\r\n

    Dear Members of the Admissions Committee,<\/p>\r\n

    I am pleased to write this letter of recommendation in support of Jane Doe and her application to the Master of Public Policy program at Simon Fraser University. I had the privilege of teaching Jane in CMNS 1115: Business Communication<\/em>, and I can say with confidence that she was one of the most engaged and capable students in the class.<\/p>\r\n

    From the outset of the term, Jane demonstrated a keen ability to grasp complex communication principles and apply them with clarity and precision. Her written work was consistently well-structured, persuasive, and insightful\u2014qualities that are essential for success in public policy. She approached assignments thoughtfully, often bringing a level of depth and analysis that exceeded undergraduate expectations. Whether crafting professional reports, delivering presentations, or participating in peer reviews, she stood out for both her intellectual rigor and her collaborative spirit.<\/p>\r\n

    What particularly impressed me about Jane was her ability to connect theory to practice. She exhibited a strong awareness of the broader social and institutional contexts in which communication operates\u2014an awareness that I believe will serve her well in a graduate policy program. She asked probing questions, demonstrated an ethical sensibility in her discussions, and engaged meaningfully with her peers.<\/p>\r\n

    In addition to her academic strengths, Jane was a respectful, conscientious, and mature presence in the classroom. Her professionalism and genuine curiosity set a tone that elevated the learning environment for everyone.<\/p>\r\n

    I have no doubt that she will thrive in the Master of Public Policy program and make meaningful contributions to the academic and professional community at SFU. I offer my full endorsement of her application and would be happy to provide further information if needed.<\/p>\r\n<\/td>\r\n

    		Human version<\/strong><\/span>\r\n\r\nDear Members of the Admissions Committee,\r\n\r\nRe: Jane Doe \u2014 Master of Public Policy program\r\n\r\nI am writing to offer my highest recommendation for Jane Doe\u2019s admission to the Master of Public Policy program at Simon Fraser University. As her communications instructor at Douglas College, I had the pleasure of teaching Jane in 2021, though I wish I could have taught her again and again. She so thoroughly enriches the post-secondary learning environment, both for her instructor and her peers, that one always hopes to have her as a student in yet another course.\r\n\r\nAs part of the course where I taught Jane, teams of students were tasked with creating a public policy proposal for a real client group, based at Central Queensland University in Australia through a Cooperative Online International Learning (COIL) project. Students reviewed the client\u2019s policy needs and prepared meaningful public policy research and recommendations to advance their client\u2019s government relations efforts. In this work, Jane demonstrated excellent critical thinking and a natural ability to analyze complex policy issues, synthesizing them into clear, well-argued recommendations.\r\n\r\nIn that group project, Jane took on a leadership role, ensuring that every team member was engaged and contributing to the learning experience and the production of work. She organized the team and its workload, mediated differing opinions, and motivated her peers to complete the project on time and at a high quality, meeting the client\u2019s needs.\r\n\r\nBeyond academics, Jane was deeply involved in extracurricular activities, including her role as a Director of the Douglas Students' Union (DSU). In this capacity, she advocated for students by organizing awareness campaigns, delivering class talks on key initiatives, and engaging directly with the student body to ensure their voices were represented in decision-making processes. Balancing these responsibilities with her academic pursuits demonstrated discipline, focus, and dedication.\r\n\r\nI have every confidence that Jane will excel in the Master of Public Policy program at SFU. Her leadership, intellect, spirit of civic contribution, and dedication make her an outstanding candidate and a value-adding asset to the learning environment.\r\n\r\nPlease feel encouraged to contact me if you wish to hear more accolades about Jane. I can be reached at myreal@emailaddress.ca or at 987-654-3210.<\/td>\r\n<\/tr>\r\n<\/tbody>\r\n<\/table>\r\nWhat differences do you notice between the two versions? Here are the differences I see:\r\n\r\nSpecificity:<\/strong> My version mentions assignments, partnerships, extracurricular activities, and details that ChatGPT couldn't have known about. With a more detailed prompt, perhaps ChatGPT could have included them, but would it have described the details correctly? You would need to be careful in checking that.\r\n\r\nTone and Style:<\/strong> My version communicates a warmth and fondness for the student that ChatGPT doesn't capture and wouldn't do a good job of. The narrative style is expressive, even playful (also showing the reader that it wasn't simply lazily created with generative AI).\r\n\r\nHigh-level Skills and Traits:\u00a0<\/strong>Again, ChatGPT looks at what a good student should do and predicts what would merit a recommendation. My version treats the student as a unique individual and names specific leadership traits, approaches to team work, and civic advocacy.\r\n\r\nInvitation for Direct Communication:\u00a0<\/strong>ChatGPT wraps up the letter and calls it done. I offer contact information and invite the reader to continue the conversation.\r\n\r\n \r\n\r\nWhich reference letter would you want written about you?<\/strong><\/span>\r\n\r\n \r\n\r\n[h5p id=\"21\"]\r\n\r\n \r\n\r\nSo much of what is described above boils down to this: ChatGPT will save you time and effort, but you must intervene to ensure you\u2019re posting quality content. As the program wrote previously, \u201cwhile ChatGPT is a powerful tool for generating text and assisting with various tasks, it lacks the depth, authenticity, understanding, and genuine creativity that humans bring to their writing. It\u2019s important to recognize its limitations and use it as a complement to, rather than a replacement for, authentic human writing.\u201d\r\n\r\nFor a much more in-depth look at writing with generative artificial intelligence, I recommend reading\u00a0GenAI Teaching and Learning Toolkit<\/em> by Gwen Nguyen.<\/a>\r\n

    Attributions<\/h1>\r\nThis chapter was adapted from Social Media & Reputation Management<\/em><\/a> by Sam Schechter, which is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.\r\n\r\nOpenAI. (2023).\u00a0ChatGPT<\/em> (Version 3.5) [Large language model]. https:\/\/chat.openai.com\/chat<\/a>","rendered":"

    ChatGPT, while advanced and capable of generating coherent and contextually relevant text, still has several limitations that make it inferior to authentic human writing. Here are some key ways in which ChatGPT falls short:<\/p>\n

      \n
    1. Lack of True Understanding<\/strong>: ChatGPT doesn\u2019t truly understand the text it generates. It lacks genuine comprehension and is simply predicting what words and phrases are likely to come next based on patterns in the data it was trained on. Humans possess deep understanding, emotions, and the ability to connect ideas in a nuanced and meaningful way.<\/li>\n
    2. No Personal Experience or Creativity<\/strong>: ChatGPT lacks personal experiences, emotions, and creativity that humans bring to their writing. It doesn\u2019t have genuine thoughts, feelings, or unique perspectives to draw from.<\/li>\n
    3. Limited Contextual Awareness<\/strong>: While ChatGPT can maintain a short-term context in a conversation, it can struggle with maintaining a deep, nuanced understanding of long conversations or intricate topics. It may sometimes provide responses that sound relevant, but are contextually incorrect or inappropriate.<\/li>\n
    4. Inaccurate Information and Biases<\/strong>: ChatGPT can generate inaccurate or outdated information since its responses are based on the data it was trained on. Additionally, if the training data contains biases, the model might inadvertently generate biased or prejudiced content.<\/li>\n
    5. Unsatisfactory Flow and Coherence<\/strong>: Although ChatGPT can produce coherent sentences, it sometimes struggles with maintaining a natural flow of thought, resulting in responses that may seem stilted or disjointed compared to human writing.<\/li>\n
    6. Limited World Knowledge and Creativity<\/strong>: ChatGPT\u2019s knowledge is limited to what it was trained on up until September, 2021. It lacks access to new information and developments that have occurred since then. Moreover, while it can mimic creativity to some extent, its creative output is often based on patterns in the training data, rather than genuine imagination.<\/li>\n
    7. Empathy and Emotional Depth<\/strong>: Humans can infuse their writing with genuine empathy, emotional depth, and understanding of the human experience. ChatGPT lacks true emotions and can\u2019t empathize in the same way.<\/li>\n
    8. Subjective and Aesthetic Judgments<\/strong>: Humans can make subjective judgments about aesthetics, art, beauty, and emotions that go beyond the scope of ChatGPT\u2019s capabilities.<\/li>\n
    9. Adaptation to Individual Styles<\/strong>: Humans can adapt their writing to various styles, tones, and preferences of the intended audience. ChatGPT\u2019s style may sometimes be inconsistent or not align well with specific audiences.<\/li>\n
    10. Errors and Misinterpretations<\/strong>: While humans can often catch errors, ambiguities, or misunderstandings in their writing, ChatGPT can generate responses that are grammatically incorrect, factually wrong, or contextually inappropriate without realizing it.<\/li>\n
    11. Dynamic and Evolving Responses<\/strong>: Humans can engage in dynamic, evolving conversations, responding to changing contexts and adjusting their responses accordingly. ChatGPT may struggle to adapt to rapidly shifting conversational dynamics.<\/li>\n<\/ol>\n

      In summary, while ChatGPT is a powerful tool for generating text and assisting with various tasks, it lacks the depth, authenticity, understanding, and genuine creativity that humans bring to their writing. It\u2019s important to recognize its limitations and use it as a complement to, rather than a replacement for, authentic human writing.<\/p>\n

      \n

      Everything above that line was written by ChatGPT in response to this prompt: \u201cIn what ways is ChatGPT inferior to authentic human writing?\u201d The only edits above were to correct for punctuation errors (yes, ChatGPT messes up its punctuation sometimes).<\/p>\n

      So, if those are the problems, how can ChatGPT help professional communicators produce quality content?<\/p>\n

      Brainstorming<\/h3>\n

      There\u2019s nothing I particularly disagree with up there and I doubt I would have thought of all those problems with ChatGPT on my own (though it was a bit repetitive at times).<\/p>\n

      That\u2019s the first hint about writing with ChatGPT. It\u2019s good at gathering a range of ideas that you might not have thought of all by yourself. ChatGPT is good at brainstorming.<\/p>\n

      The pressure to constantly dream up new content can be frustrating, especially as you get the feeling that you have already created similar content in the past. ChatGPT can help you come up with some new content ideas.<\/p>\n

      Outlining<\/h3>\n

      Similar to brainstorming, ChatGPT will suggest an order for how information should be provided. It might need to be corrected, but it\u2019s a starting point for how to organize your longer content, such as a blog article. When creating outlines, it sometimes has problems in its organization and hierarchy; information that should be a subsection is presented as a major section and information that should be a major section is presented as a subsection. Also, content can easily be replicated across more than one section (ChatGPT has lousy memory).<\/p>\n

      Speed<\/h3>\n

      Even the most prolific writers with the quickest fingers in the planet would be hard pressed to produce quality original content at faster than 50 words per minute. (Yes, folks can type faster, but as they do, their ability to focus on quality content goes down.)<\/p>\n

      On the other hand, ChatGPT can produce about 400 words of passable\u2014though rarely great\u2014content in a few seconds. But there\u2019s the problem again: a large amount of quickly available text is only good if the text is good; it\u2019s mostly in the range of \u201cokay.\u201d<\/p>\n

      What does that mean for professional writers? ChatGPT can increase the speed of producing draft paragraphs. As noted above, ChatGPT loses the plot after a while, so you can\u2019t use it to produce a first draft of a long document, but you can use it to produce a few paragraphs, or perhaps one contained section, as seen above.<\/p>\n

      Given the problems, you\u2019ll need to re-write those paragraphs to inject emotion and examples. If stating information that needs to be cited, you’ll need to verify the accuracy of the information, correct as necessary, and cite an authority for the relevant information. ChatGPT cannot be trusted to be factual or accurate. You\u2019ll need to make sure there\u2019s continuity from one section to the next. But you\u2019ll have a bit of draft material to work with more quickly.<\/p>\n

      Availability<\/h3>\n

      Your generative-AI writing assistant never sleeps and never takes a day off. We mortal humans, on the other hand, need sleep and days off. Without that, our writing quality gets worse and worse.<\/p>\n

      Appropriateness<\/h3>\n

      As a follow-up to the previous paragraph, ChatGPT never talks trash or drunk posts. The program is less likely to make embarrassing typos from fatigue or intoxication. For example, how easily can you post about your organization\u2019s pubic places, instead of its public<\/em>\u00a0places? Oops for you, but that\u2019s a mistake ChatGPT is unlikely to make.<\/p>\n

      A mistake ChatGPT will sometimes make, though, is to produce content that is politically problematic, such as reinforcing negative, sexist, or racist stereotypes. That must be accounted for and corrected.<\/p>\n

      Enhancing Vocabulary<\/h3>\n

      In the same way that ChatGPT can help with brainstorming, it can help with rephrasing and vocabulary. The program can be asked to explain something better or with new word choices. In this way, it\u2019s like a thinking thesaurus.<\/p>\n

      Role Playing<\/h3>\n

      If you\u2019re wondering how your audience might respond to a post, try asking ChatGPT. Ask the program how a well-defined audience (give some demographic and other information about the audience) would respond to content you\u2019ve drafted. Try it out with a few different target audiences. Let this help you anticipate how people might engage with your content. Revise to get the results you want and see what happens.<\/p>\n

      And Now, Words of Caution<\/h2>\n

      Yes, ChatGPT (and competing products) is great, but never outsource your critical thinking. Students are well advised to do their own brainstorming and outlining before<\/em> they consult ChatGPT. Going to ChatGPT first undermines your own ability to produce better results because your brain will get lazy when it has a quick, simple, relatively good option made available.<\/p>\n

      To illustrate this point, let me share a story. A former student of mine asked me for a reference letter (this happens often enough when you teach at a college\/university). As always, my response was this: “sure, but please write me the first draft of what you want in your reference letter.” She promptly went to ChatGPT and sent me the content on the left. Because I cared about her and was willing to forgive this lazy approach for a special student, I produced the version on the right. Take a look at the differences and note where a human voice offers an improved written product.<\/p>\n\n\n\n
      \n

      ChatGPT version<\/strong><\/span><\/p>\n

      Dear Members of the Admissions Committee,<\/p>\n

      I am pleased to write this letter of recommendation in support of Jane Doe and her application to the Master of Public Policy program at Simon Fraser University. I had the privilege of teaching Jane in CMNS 1115: Business Communication<\/em>, and I can say with confidence that she was one of the most engaged and capable students in the class.<\/p>\n

      From the outset of the term, Jane demonstrated a keen ability to grasp complex communication principles and apply them with clarity and precision. Her written work was consistently well-structured, persuasive, and insightful\u2014qualities that are essential for success in public policy. She approached assignments thoughtfully, often bringing a level of depth and analysis that exceeded undergraduate expectations. Whether crafting professional reports, delivering presentations, or participating in peer reviews, she stood out for both her intellectual rigor and her collaborative spirit.<\/p>\n

      What particularly impressed me about Jane was her ability to connect theory to practice. She exhibited a strong awareness of the broader social and institutional contexts in which communication operates\u2014an awareness that I believe will serve her well in a graduate policy program. She asked probing questions, demonstrated an ethical sensibility in her discussions, and engaged meaningfully with her peers.<\/p>\n

      In addition to her academic strengths, Jane was a respectful, conscientious, and mature presence in the classroom. Her professionalism and genuine curiosity set a tone that elevated the learning environment for everyone.<\/p>\n

      I have no doubt that she will thrive in the Master of Public Policy program and make meaningful contributions to the academic and professional community at SFU. I offer my full endorsement of her application and would be happy to provide further information if needed.<\/p>\n<\/td>\n

      		Human version<\/strong><\/span><\/p>\n

      Dear Members of the Admissions Committee,<\/p>\n

      Re: Jane Doe \u2014 Master of Public Policy program<\/p>\n

      I am writing to offer my highest recommendation for Jane Doe\u2019s admission to the Master of Public Policy program at Simon Fraser University. As her communications instructor at Douglas College, I had the pleasure of teaching Jane in 2021, though I wish I could have taught her again and again. She so thoroughly enriches the post-secondary learning environment, both for her instructor and her peers, that one always hopes to have her as a student in yet another course.<\/p>\n

      As part of the course where I taught Jane, teams of students were tasked with creating a public policy proposal for a real client group, based at Central Queensland University in Australia through a Cooperative Online International Learning (COIL) project. Students reviewed the client\u2019s policy needs and prepared meaningful public policy research and recommendations to advance their client\u2019s government relations efforts. In this work, Jane demonstrated excellent critical thinking and a natural ability to analyze complex policy issues, synthesizing them into clear, well-argued recommendations.<\/p>\n

      In that group project, Jane took on a leadership role, ensuring that every team member was engaged and contributing to the learning experience and the production of work. She organized the team and its workload, mediated differing opinions, and motivated her peers to complete the project on time and at a high quality, meeting the client\u2019s needs.<\/p>\n

      Beyond academics, Jane was deeply involved in extracurricular activities, including her role as a Director of the Douglas Students’ Union (DSU). In this capacity, she advocated for students by organizing awareness campaigns, delivering class talks on key initiatives, and engaging directly with the student body to ensure their voices were represented in decision-making processes. Balancing these responsibilities with her academic pursuits demonstrated discipline, focus, and dedication.<\/p>\n

      I have every confidence that Jane will excel in the Master of Public Policy program at SFU. Her leadership, intellect, spirit of civic contribution, and dedication make her an outstanding candidate and a value-adding asset to the learning environment.<\/p>\n

      Please feel encouraged to contact me if you wish to hear more accolades about Jane. I can be reached at myreal@emailaddress.ca or at 987-654-3210.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

      What differences do you notice between the two versions? Here are the differences I see:<\/p>\n

      Specificity:<\/strong> My version mentions assignments, partnerships, extracurricular activities, and details that ChatGPT couldn’t have known about. With a more detailed prompt, perhaps ChatGPT could have included them, but would it have described the details correctly? You would need to be careful in checking that.<\/p>\n

      Tone and Style:<\/strong> My version communicates a warmth and fondness for the student that ChatGPT doesn’t capture and wouldn’t do a good job of. The narrative style is expressive, even playful (also showing the reader that it wasn’t simply lazily created with generative AI).<\/p>\n

      High-level Skills and Traits:\u00a0<\/strong>Again, ChatGPT looks at what a good student should do and predicts what would merit a recommendation. My version treats the student as a unique individual and names specific leadership traits, approaches to team work, and civic advocacy.<\/p>\n

      Invitation for Direct Communication:\u00a0<\/strong>ChatGPT wraps up the letter and calls it done. I offer contact information and invite the reader to continue the conversation.<\/p>\n

       <\/p>\n

      Which reference letter would you want written about you?<\/strong><\/span><\/p>\n

       <\/p>\n

      \n