My Early Days With AI, Part 2

The Honeymoon Period

[A quick word or two before starting this AI Field Note. I may not have been clear in the first Note that these first few posts are covering the time prior to last week’s launch. The Honeymoon Period was the first week of September, when I was auditioning the chatbots and ended up with one quick draft and one finished vignette. I will have two or three more Notes to cover the AI experience while planning and designing the Substack and WordPress sites. These first AI Field Notes are being written from notes I made at the time and the chat transcripts. After this, the plan is for them to be written contemporaneously with the Memoir Project vignettes.

While the experimental use of AI is integral to writing the Memoir vignettes, all writing of the Field Notes is my own. (Though it might be fun sometime to see what we get if I ask the chatbot to report on itself!) The blog posts in My 2 Cents are also my writing, though I am using chatbots for research and as a copy editor.]

---

AI Field Notes for An Ordinary Day

I feel I’ve confirmed the validity of this notion—of quickly concocting an interesting narrative out of personal history, good prompts, AI historical research, AI composition, and light human editing. Now I want to do a vignette on the day I was born. I choose this because it’s a brief snapshot for which I have good information and documentation. I think of these as anchors for the context that the chatbot will supply. I also expect it will make a good prototype for working with the chatbot to come up with some kind of template to help organize and manage the torrent of text that every prompt generates.

The chatbot starts by explaining some of the relevant terms we will be using. I learn that ChatGPT is still pretty rudimentary in its organizational toolkit. There isn’t much of a hierarchy. Just folders, which are termed “Projects” and inside the folders you can have as many “Chats” as needed. There is only one level in the folder. That means no nested folders, only individual chats.

I mentioned previously that this chatbot is really chatty, right? An understatement, truly. It’s not rare for one of its 3-second responses to a prompt to give me several minutes of reading. So a chat can very quickly get very long. (This is less true in Hyperwrite AI.) I begin to recognize that it could quickly become a challenge to find specific information later. I ask how I should do that.

A few sessions from now, I’m going to get pretty frustrated with how labyrinthine this becomes, even suspecting that the chatbot is kind of making things up as we go. But reviewing my notes and the transcript now, I’m impressed with the chatbot’s giving me a simple starting place. It explains project folders and chats and gives me a naming protocol to keep things consistent between us. We’re ready to get to work.

I mentioned having documents from my birth. So, my first prompt is:

ME—In a small town private hospital in the 1940s, what would a typical process have been to record a birth and issue a birth certificate? What position on the staff would have been responsible for billing for the birth?

I get back about a page of vividly described details. I’ll also come to understand soon enough that the chatbot is programmed to end each response with an offer for one or more, usually more, next steps. (Keep in mind I have already spent a fair amount of time briefing the chatbot on the project.) This time the offer is:

ChatGPT—Would you like me to draft a vignette-style description (say, what a couple in 1948 might have experienced step by step when their baby was born in a small hospital) — something you could lift almost directly into your memoir narrative?

This chatbot is REALLY anxious to be helpful. I hadn’t asked for it, but what the heck:

ME—Sure, let’s see what it looks like.

ChatGPT—[Produces vignette-style description]

Would you like me to expand this vignette into a “typical day” narrative (from arrival at the hospital through discharge), so you could use it almost like scene-setting in a memoir chapter?

I think: Sure, let’s go with the flow.

ME—Yes.

ChatGPT—Perfect — here’s a more expansive “typical day” narrative that takes you through the whole arc, from admission through discharge, in a small-town private hospital of the late 1940s. I’ve kept it evocative, but accurate to the period:

[text of a more expansive vignette]

This gives you a scene-by-scene flow: admission → labor → delivery → recordkeeping → ward routines → billing → discharge.
Would you like me to annotate this with sources and details of “what’s historically accurate” (what we know for sure vs. where I’ve used evocative reconstruction), so you can be confident about blending fact with memoir narrative?

This could go on forever. Time to butt in.

ME—What day of the week was September 1, 1948?

ChatGPT—September 1, 1948, was a Wednesday.

ME—Can you find a photo online of Bixby Hospital in Adrian, Michigan from the 1940s or 50s?

ChatGPT—Here’s what appears to be a historic photograph of the old Bixby Hospital in Adrian, Michigan—likely dating back to the mid-20th century. The image is from a Pinterest pin titled “The Old Bixby Hospital, Adrian, MI” .

Would you like help locating archival sources or contacting local historical institutions to see if they have more dated or high-resolution images?

ME—No thanks, what you got is perfect.

ChatGPT—Great — glad that one works for you! That photo should fit nicely alongside your vignette about a 1940s hospital birth.
Do you want me to also describe the building in words (architecture, size, feel) so you can use it in your memoir without having to rely on the photo itself?

To myself: not really.

ME—Can you find the percentage of babies born in hospitals, compared to at home, in or around 1948, in Michigan and/or the United States?

ChatGPT—Here’s what the historical data reveals about the percentage of babies born in hospitals versus at home around 1948 in the United States (and insight on Michigan if available):

Like a few previous times already, my prompts tend to generate a very generous amount of relevant data and annotations. It’s far more than I could or should include, or a reader would want, but I can find one or two gems. This is the severely abridged version of the chat!

ChatGPT—Would you like help weaving this into your memoir—perhaps framing how a small-town family might have viewed hospital birth as increasingly normal by the late 1940s?

ME—I think I have that, thanks.

ChatGPT—Perfect — sounds like you’ve got what you need for that piece. 👍

Before I start the first draft, I look at my Certificate of Birth and have a thought. I ask:

ME—I’m remembering that the handwriting style common in the 1940s was called Palmer. Is that correct?

ChatGPT—Yes — you’re remembering correctly. Would you like me to pull an example image of Palmer handwriting from that era, so you can visualize what those hospital forms and ledgers would have looked like?

I was about to ask.

ChatGPT—

Here are four visual examples showcasing the Palmer Method of handwriting—each image illustrates the elegant, slanted cursive style and muscular-arm technique characteristic of this 20th-century penmanship system. (Plus another half-page on the Palmer style. Email if you’d like more detail.)

The next day I wrote my rough draft, drawing from the chat. I submitted it to the chatbot.

In seconds, I received this response:

ChatGPT—This is a very strong first draft — vivid, personal, and grounded in historical texture. I’ll give you honest, constructive feedback in three areas: strengths, suggestions, and questions to consider.

I think at this point I might still have been giving some weight to the compliments, but would soon ask the chatbot to come clean about the sucking up. It admitted that it’s just how it’s programmed. At any rate, I got some good feedback and it asked if I’d like a lightly edited, polished draft. I said yes and voila! There it was.

Then I had a thought that turned out so well, I expect it to become part of the routine:

ME—Could you place my rough draft and your revised version side by side?

Absolutely — here’s a side-by-side comparison so you can see where I tightened, rearranged, or reframed things.

I immediately have both versions in two columns within the chat. I open Word and—keeping much of mine, adding a few things from the bot’s, and combining some into new text—I rewrite the vignette and give it back for feedback. A couple of changes, then it/he/she/they gives helpful suggestions for where to place the images, and we have the first truly finished vignette for the memoir. Take a look: An Ordinary Day