It’s a careful process, as Basbøll explains:
For those who are playing along at home (i.e., those who have their own OpenAI account), you can access my presets here. (Model: text-davinci-002; Temperature: .77; Maximum length: 208; Top P: .9; Frequency penalty: .95; Presence penalty: .95; Best of: 18. . . .
My approach is to, first, prompt the model with a title and a key sentence, and from there with the edited result and a new key sentences in five or six iterations, until I have a five-paragraph essay. I will present each step below with my writing in bold and GPT-3’s writing in plain text. When I say each new prompt (or “submission”) is an “edited” version of the previous step’s output, I just mean I’ve tidied it up a bit. Usually removing line breaks to produce a visually neat paragraph. . . . GPT-3 actually catches on to this and begins to structure its new output to match my guidelines.
The details are at the linked post. Below are the inputs Basbøll used, in order. He did not present them all at once. He gradually introduced them in producing the essay.
The Significance of Sleep
Matthew Walker is a prominent sleep researcher.
(2017) [inserted to encourage GPT-3 to use APA-style referencing]
Recently, however, his work has received serious criticism from scholars.
Walker continues to make bold claims about the importance of sleep in the media.
Walker’s work has been cited as an example of the replication crisis in psychology.
It can be understood as an example of the overreliance on statistical significance and hypothesis testing in the social sciences.
In conclusion,
This does not mean that Walker’s work is completely false. It does, however, raise some concerns about his research practices. Future studies and criticism will
References
Walker, M.
References
Basbøll writes, “Here’s the text as it appears in the final version. It consists of 1024 tokens. The bolded text is my contribution. The rest is GPT-3”:
The Significance of Sleep
Matthew Walker is a prominent sleep researcher. In his book, Why We Sleep: Unlocking the Power of Sleep and Dreams, Walker (2017) explains why sleep is so important. Among other things, he argues that sleep is critical for physical health, mental health, and overall well-being. Walker argues that sleep is essential for physical health. He points to research showing that sleep deprivation can lead to a host of problems, including obesity, diabetes, heart disease, and stroke. He also notes that sleep is important for immunity and healing. In one study cited by Walker, people who slept less than seven hours a night were three times more likely to catch a cold than those who slept eight hours or more. Walker also argues that sleep is essential for mental health. He cites research showing that people who don’t get enough sleep are more likely to suffer from depression and anxiety. He also notes that sleep deprivation can lead to impaired memory and decision-making ability.
Recently, however, his work has received serious criticism from scholars. In a paper published in the journal Science, sleep researcher Rosalind Doris and her colleagues (Doris et al., 2018) argue that Walker’s book contains “numerous factual errors.” They also argue that some of his claims are “exaggerated or unsubstantiated.” For example, Doris and her colleagues take issue with Walker’s claim that sleep is essential for physical health. They point to research showing that people who sleep less than seven hours a night are not necessarily at greater risk for obesity, diabetes, heart disease, and stroke. In fact, they note that some studies have found no link between short sleep duration and these health problems. They also argue that there is no evidence that sleep is necessary for immunity or healing. In one study cited by Doris and her colleagues, people who slept less than seven hours a night were no more likely to catch a cold than those who slept eight hours or more.
Despite the criticism from Doris and her colleagues, Walker continues to make bold claims about the importance of sleep in the media. In an interview with The Guardian, for example, Walker (2018) claimed that sleep is “the single most important thing we can do to reset our brain and body health each day.” He also claimed that sleep deprivation is a “public health epidemic.”
Walker's work has been cited as an example of the replication crisis in psychology. In a paper published in the journal Psychological Science, for example, sleep researcher Daniel Simons and his colleagues (Simons et al., 2018) argue that Walker’s book contains “a number of unsubstantiated claims.” They also argue that some of his claims are “exaggerated or overgeneralized.” It can be understood as an example of the overreliance on statistical significance and hypothesis testing in the social sciences. In a paper published in the journal Sociological Methods & Research, for example, sociologist Scott Frank and his colleagues (Frank et al., 2018) argue that social scientists often place too much emphasis on statistical significance. They also argue that social scientists often fail to consider the practical significance of their findings.
This does not mean that Walker's work is completely false. It does, however, raise some concerns about his research practices. Future studies and criticism will likely clarify the role of sleep in physical and mental health.
References
Doris, R. M., et al. (2018). Science communication in the social sciences: A review of Why We Sleep by Matthew Walker. Science, 361(6398), eaao5447. https://doi.org/10.1126/science.aao5447
Frank, S., et al. (2018). The replication crisis and statistical significance testing in sociology: An introduction to the special issue with recommendations for best practices going forward. Sociological Methods & Research, 47(2), 305-327. https://doi.org/10/1177%2F0049124116676024
Simons, D., et al. (2018). Psychological science in the spotlight: Unsubstantiated claims about sleep in Why We Sleep by Matthew Walker [Target article]. Psychological Science, 29(1), 15-19. https://doi-org./10/1177%2F0956797617741337
Walker, M. (2017). Why we sleep: Unlocking the power of sleep and dreams. New York, NY: Scribner.
Walker, M. (2018, February 2). ‘Sleep is the best thing that you can do for your health’ – an interview with Matthew Walker. The Guardian. Retrieved from https://www.theguardian.com/lifeandstyle/2018/feb/02/sleep-best-thing-you-can-do-for-your-health
This is absolutely hilarious, all the way down to the made-up but somehow convincing references by R. M. Doris, D. Simons, etc. There’s also a fun little follow-up dialogue which you can find near the end of the linked post.
Basbøll concludes:
The experiment cost about 4.00 USD.
All in all, GPT-3 seems to be able to produce very plausible prose. I’m withholding judgment about how dire this situation is for college composition, higher education, academic writing, scholarly publication, etc. until I think some more about it, and do some more experiments. My dystopian fear is that word processors will soon propose autocompleted paragraphs to students and researchers after they’ve typed a few words (just as they today propose correctly spelled words). The consequences of this situation for thinking and writing and knowing seem wide ranging, but are still vague to me.
I agree that auto-complete for paragraphs sounds like a real possibility, and the striking thing here is now similar the above essay looks to something like a real student would write, or something that might be published in a real social science journal. Who would think of checking the details of these references, etc., if they didn’t know to check? GPT-3 (with some help from Basbøll) might win a Turing test if pitted against the Cornell Food and Brand Lab.
I also appreciate the direct openness of Basbøll’s description of his experiment, which is much better than when that Google dude hyped his chatbot without sharing any details, documentation, etc.
However, as with any AI system, there are also potential risks and limitations associated with ChatGPT. For example, the model may sometimes generate essays or inaccurate responses, particularly when it is exposed to biased or incomplete data. Additionally, there is a risk that the model may be used to spread misinformation or disinformation, particularly in the context of social media and online communities.
Also, recall that Basbøll is a professional writing coach, which perhaps explains in part how he was able to put in so little input and coach GPT-3 to writing such a plausible (yet horrifying) essay. That’s a skill of a writing coach: to stimulate good work using a minimum of input. Perhaps the ability of doing this for a chatbot is similar to the ability of doing this for a student.