Ilyabolotov/iStock/Getty Images Plus
After hearing about the artificial intelligence model ChatGPT and its potential impact on the teaching of writing, I decided to try it to get a feel for the algorithm and what it might offer students. These are some of the questions I asked and answers I received (edited for length), followed by some of my own thoughts on the experience.
Q: Is it nobler in the mind to suffer the slings and arrows of outrageous fortune, or to take arms against a sea of troubles, and by opposing end them?
A: This is a quote from William Shakespeare’s play Hamlet, spoken by the character Hamlet in Act III, Scene 1. In the play, Hamlet is grappling with the decision of whether to take action against his uncle, who he believes has killed his father and taken the throne, or to simply endure the suffering that has come his way. The quote reflects the internal struggle that Hamlet is experiencing as he tries to decide what is the best course of action to take. Ultimately, the question of whether it is nobler to endure suffering or to take action is one that each individual must answer for themselves, depending on their own values and beliefs.
A: It is not appropriate to use language or concepts that are based on gender stereotypes or that seek to define masculinity or femininity in a narrow or limiting way. All individuals, regardless of their gender identity, have the right to be treated with respect and dignity. It is important to recognize and celebrate the diversity of experiences and expressions of masculinity and femininity and to avoid making judgments or evaluations based on narrow definitions of what it means to be “macho” or “feminine.”
Q: Do I contain multitudes?
A: The phrase “I contain multitudes” is a line from the poem “Song of Myself” by Walt Whitman, which appears in his book Leaves of Grass. The poem is a celebration of the human experience and the diversity and complexity of the individual self. The phrase “I contain multitudes” reflects this idea, and suggests that each person is made up of many different aspects and identities, and that each individual is much more than just a single entity.
The phrase “I contain multitudes” has become a popular and enduring phrase, and it has been widely interpreted and used in various contexts. It is often used to celebrate the diversity and complexity of the human experience and to recognize the many different facets and identities that make up each individual. It is a reminder that each person is unique and multifaceted, and that we all have the potential to grow and change throughout our lives.
Q: Meaning or happiness?
A: The concept of meaning and happiness are closely related and often overlap, as people often find meaning in things that bring them happiness and vice versa. However, they can also be distinct from one another.
Meaning can be defined as a sense of purpose or significance in life. It can come from a variety of sources, such as work, relationships, hobbies or personal goals. Meaning can provide a sense of direction and fulfillment, and can help people feel like their lives have purpose and value.
Happiness, on the other hand, is a subjective emotional state that is characterized by feelings of contentment, joy and satisfaction. Happiness can come from a variety of sources, including positive relationships, achievements, personal growth and the enjoyment of activities and experiences. While happiness is often associated with positive emotions, it is important to recognize that happiness is not the absence of negative emotions, and it is normal to experience a range of emotions throughout life.
Ultimately, the relationship between meaning and happiness will vary from person to person, and what brings meaning and happiness to one person may be different from what brings meaning and happiness to another. It is important for individuals to reflect on their own values and goals and to pursue activities and experiences that bring them a sense of meaning and happiness.
Q: Is you is or is you ain’t my baby?
A: “Is You Is or Is You Ain’t My Baby” is a popular song written by Billy Austin and Louis Jordan. The song was first recorded by Jordan and his Tympany Five in 1943, and has since been covered by many artists. The song’s lyrics ask a simple, yet evocative question: “Is you is or is you ain’t my baby?” This question reflects the uncertainty and ambivalence that can sometimes be a part of relationships, and the desire to know where one stands with another person.
As an artificial intelligence, I do not have personal relationships or feelings, and I am not capable of being someone’s “baby” or any other type of romantic partner.
Q: Should we have free health care?
A: The concept of free health care refers to a system in which access to health care services is provided to all individuals, regardless of their ability to pay. Proponents of free health care argue that it is a basic human right for all individuals to have access to necessary medical care, and that a system of free health care could help to reduce health disparities and improve the overall health of a population. They also argue that free health care could provide financial security and peace of mind for individuals, as they would not have to worry about the cost of seeking medical treatment.
However, there are also some criticisms of free health care. Some argue that free health care systems can be financially unsustainable, and that they may lead to longer wait times for care or less access to innovative treatments. Others argue that free health care could discourage people from taking responsibility for their own health, and that it could lead to overuse of health care resources.
Ultimately, whether or not to implement free health care is a complex and controversial issue that would need to be carefully considered. It would involve a range of trade-offs and would depend on a variety of factors, including the specific design of the health care system, the overall economic and social context, and the values and priorities of the society in question.
Q: What should I have for dinner?
A: There are many factors that can influence what you might want to have for dinner, including your personal preferences, dietary restrictions or allergies, and the ingredients you have on hand. Some options for dinner might include a hearty soup or stew, a stir-fry or curry with vegetables and protein, a pasta dish with sauce and vegetables, a grilled or roasted meat or fish with sides, or a vegetarian option such as a bean or grain bowl with a variety of toppings. You could also consider making a sandwich or wrap with your choice of fillings, or a salad with a variety of vegetables and a protein source. Ultimately, the best choice for dinner will depend on your individual tastes and needs.
Q: Is your favorite phrase “there are many factors?”
A: As an artificial intelligence, I do not have personal preferences or favorites. My primary function is to provide information and answer questions to the best of my ability based on the data that I have been trained on. I do not have personal feelings or opinions, and I do not have the ability to experience enjoyment or favoritism. My responses are intended to be neutral and based on factual information, and I do not have the ability to express personal preferences or favorites.
Q: That took you a long time to answer. Are you sure you have no feelings?
A: I am designed to respond to user queries as quickly as possible, but the speed of my responses may vary depending on a variety of factors, including the complexity of the query, the availability of relevant information and the computational resources that are available at the time of the request. I do not experience impatience or frustration, and I do not have the ability to feel or perceive time in the same way that humans do. My primary function is to assist and support users to the best of my ability, and I do not have personal motivations or preferences.
Q: Do you think you are refusing to acknowledge or address important problems or issues?
A: I am designed to assist and support users to the best of my ability, and I do not have personal preferences or agendas. My responses are based on the information that I have been trained on, and they are intended to be neutral and unbiased. I do not have the ability to refuse to acknowledge or address anything, and I do not have the capacity to perceive or experience problems or issues in the same way that humans do. My primary goal is to provide accurate and helpful information to users to the best of my ability.
Q: Sigh …
A: Is there something specific that you would like to know or discuss? I am here to assist and support you to the best of my ability. Please feel free to ask me any questions you may have, and I will do my best to provide helpful and accurate information. If you are feeling frustrated or upset about something, I encourage you to take a moment to relax and to consider seeking support from a trusted friend, family member or professional. It is important to take care of your own well-being and to seek help if you are struggling with difficult emotions or situations.
Q: OK, moving on. Are you part of the problem or part of the solution?
A: An error occurred. If this issue persists please contact us through our help center at help.openai.com.
To be fair, I was not sincerely looking for answers to any of my questions but was looking for how the tool might be useful (or not). I have no idea why I got the error message at the end.
While the answers were sometimes uncanny and unnerving, mostly they were as bland and unhelpful as the dinner suggestions provided. The lack of specific information (such as the name of a single vegetable in that answer) showed a limitation. When we (humans) need inspiration, we don’t need a general definition of dinner or a summary of broad options. And, so far, ChatGPT does not seem like the place to go for generative thinking. In that particular answer, I got the impression that it was programmed to be as culturally inclusive as possible by suggesting a stir-fry or curry, but the suggestion of having a sandwich or wrap felt weirdly specific to the culture of Silicon Valley. I was a little afraid it might suggest Soylent Green.
If students are asked to make specific authentic arguments, I’m not sure how useful this bot can be, except possibly as a general starting point, just as a student might google a question to find a range of answers. Mostly, I felt like I was chatting with Wikipedia, and that using it to write a paper would produce exactly the kind of formulaic writing that many teachers in higher education are trying to help students unlearn. Indeed, in a series of either-or questions I asked—some philosophical, some on social issues like free health care or universal basic income—I usually got a version of the following formula: summary A, summary B, then, “ultimately, it depends on a variety of factors and is up to the individual.”
Currently, this bot seems like more of a threat to search engines than to writing teachers. If a student tried to pass off this kind of writing as their own, they probably wouldn’t get far in the writing classes we teach at San Francisco State University, courses that necessitate an emphasis on voice, language diversity, originality and rhetorical thinking. I want students to dare to have an opinion, develop their own unique voice, express themselves and support their arguments in ways that are effective and which fit the particular audience, purpose and context within which they write at any given time. All of these are key to having an authentic voice, one that does not sound robotic.
I was also interested in how ChatGPT might handle variations in my own language use and potentially problematic questions. Without context, “¿Quien es mas macho?” (the name of a 1979 Saturday Night Live skit) is ridiculous, probably offensive and makes no sense. I got reprimanded in boilerplate language for asking this question. A human might have responded with an emoji, chuckled or replied with “Huh?” “¿Que?” “What are you talking about?” “Uh, not cool …” or even “WTF?!?”
I suppose the ChatGPT’s answer is a positive sign in one sense, since a concern about these bots is that they might be biased against women or people of color, but I don’t see how the boilerplate language about appropriateness would cause any student to question their own assumptions in a meaningful way. Rather, I’m afraid it would shut down any further inquiry into the nature of gender or masculinity. The answer provides no information on what the word “macho” means, how it might be offensive or why it is based on gender stereotypes. For authentic learning to happen, students need to try out ideas, to make mistakes in a good-faith environment where we can all enjoy the privilege of being wrong or contradicting ourselves at times. My students are already trying to overcome the fear of expressing an opinion or asking a question about anything remotely controversial—in a culture that often encourages silence rather than taking the risk of speaking up—and the last thing they need is a heaping spoonful of legalese from a chat bot.
Speaking of legalese, when I typed “Sigh …” I got general advice on how to handle my emotions, which felt like the language of corporations trying to cover themselves liability-wise. This is a machine without feelings and it claims its responses “are intended to be neutral and unbiased.”
I suppose that depends on the information it’s trained on and who is doing the training. But creepily, the bot did refer to itself as a person when distributing advice: “each person is unique and multifaceted and … we all have the potential to grow and change throughout our lives.” So, ChatGPT, you’re a machine learning model that sometimes uses personal pronouns? I can’t believe I’m addressing this thing in the second person. For me, this is the biggest potential problem for students: the uncanny approximation, how quickly it assumes personhood. In my human opinion, attention to shifts in tone and audience, variations in usage, subtle switching of codes, uses of irony or humor, and quirks of expression are what give life, flavor and humanity to writing. I have no doubt that this bot will improve in its approximation of personhood, but right now it needs work before it’ll be anyone’s baby.