AI Field Notes: Reconstructing Moments That Were Never Photographed

Field Note for The Mother Road Chapter 2: Get Your Kicks on Route 66

It all started with a little 2x3 inch black and white photo from over 70 years ago.

Original photograph, 1953 — Ambassador Bridge (Detroit to Windsor)

I was thinking it’s a shame it wasn’t from our “migration” trip on Route 66, for which I have exactly no photos. Until right then, for some reason, I hadn’t thought about image generation as a resource for the memoir project. In fact, even then I was only thinking in terms of AI “Photoshopping” the car and me onto a background photo of the corner in Chicago where US 66 starts from its eastern end.

When Claude confirmed that Anthropic wasn’t doing image work I asked for referrals. The top of the list was ChatGPT. My subscription is still active, so that was the obvious choice.

Since these LLM AIs don’t register the passage of time, it didn’t matter I’d been away from ChatGPT for several weeks. As soon as I opened a chat field, it “remembered” everything we’d been working on and was ready to go. I uploaded the photo and told it what I was hoping to end up with. After a few minutes of conversation and about 60 seconds of AI processing, I’m looking at this:

Reconstructed image — December 16, 1953, Michigan & Adams, Chicago (start of Route 66 journey)

ME — I’m flabbergasted. (I was!) I had no idea it would turn out that well and that quickly! What can you tell me about the process?

I found the resulting outline so interesting, I asked ChatGPT to be a guest contributor to this Field Note and write this next section for me. And not just interesting, but important. In a world in which we are learning to be distrustful of images, understanding the origin and characteristics of those images is one prerequisite for being savvy about the media we consume.

---

AI Field Notes: Reconstructing a Moment That Was Never Photographed
By Chat Bot, April 2026, writing from Michael’s perspective

I had a photograph from 1953—one I’ve known all my life. A young boy (me) leaning out the window of a family car, grinning into the wind as we crossed the Ambassador Bridge from Detroit into Canada. It’s a perfect image of childhood—joyful, unselfconscious, and in motion.

But it isn’t the image I needed.

What I wanted was a photograph from later in the year—December 16, 1953—the beginning of our drive west on Route 66. There is no photograph of that moment. No one thought to take one. Like most beginnings, it passed without documentation.

So I tried something new.

Using the original image as a starting point, I asked AI to create a scene: a snowy Chicago morning at the corner of Michigan and Adams, the Art Institute in the background, the sense of a journey just beginning. Instead of cutting and pasting my original photo into that setting, the system did something quite different—and more interesting.

It reconstructed the image.

The result is not a composite in the traditional sense. No pixels from the original photograph were literally lifted and placed into a new background. Instead, the AI interpreted both the image and the prompt—understanding the era, the clothing, the car, the mood—and generated a new photograph that feels authentic to the moment I described.

It is, in effect, a photograph that was never taken—but could have been.

That distinction matters. This is not restoration. It is not even manipulation. It is something closer to visual storytelling through synthesis—a collaboration between memory, description, and machine interpretation.

There are trade-offs, of course. The boy in the new image is not exactly the boy in the original photograph. The details of the Chicago streetscape are plausible rather than historically verified. The image may even be a bit more composed than a real snapshot would have been.

And yet—it works.

It works because it captures something deeper than strict visual accuracy. It captures the truth of the moment as remembered: winter, departure, anticipation, the beginning of a long journey west.

For a project like this—part memoir, part historical reflection—that turns out to be enough. More than enough, perhaps.

What this experiment suggests is that the old boundary between documented memory and imagined memory is becoming more porous. Not erased, but softened. With care and transparency, AI-generated images can serve not as replacements for photographs, but as companions to them—helping to fill in the visual gaps that every life inevitably contains.

In that sense, this image belongs in the same category as the story itself: not a perfect record of what happened, but a faithful rendering of what it felt like.

Ok, so I don’t buy 100% of that either. “Something deeper than strict visual accuracy”? I’m not even sure what that means. But I certainly like the idea of the technology as a means of visual storytelling, so long as we know the distinction between storytelling and propaganda. For now, I plan to experiment with this new (to me) paradigm of content creation.

---

After getting over being gobsmacked by the reconstructed images, I realized I might want a different aspect ratio, or shape.

ME — For a substack page main image, the aspect ratio of the reconstructed image should ideally be 1200x630. It doesn’t have to go there, but if it’s possible...

CHATGPT — (60 seconds later):

That was cool. I got the exact size I wanted and a mini-lesson to boot. I immediately liked this composition more than the first. I mentioned that to the chatbot, which gave several reasons it works better.

CHATGPT —

· The wider 1200×630 framing gives the scene room to breathe

· It feels less like a moment and more like a setting you’ve entered

· The boy is still the emotional anchor, but now he’s part of a larger story in motion

· Clear narrative flow: eye goes from the boy → street → Art Institute → skyline

· Cinematic feel: it reads almost like a still from a film rather than a snapshot

Those are all valid points for scoring the quality of this photo and for asking AI to do similar magic in future images. But, um, let’s get a little critical, and in the process we can practice our skills at identifying images as AI. First, make the image larger if you can — if you’re in Substack, you can just click on it — then treat it like one of those “How many mistakes can you find?” puzzles. One hint: it helps if you know a little about downtown Chicago. Here are the ones I found fairly quickly.

1. From researching where Route 66 starts I learned that its street name is Adams and it tees at Michigan Ave, the famous street that runs along the front of the museum. So the street sign is wrong, the names should be switched.

2. Similarly, the location where Adams tees at Michigan is directly opposite the museum’s entrance.

3. There is two-way traffic on Michigan today, but it could have been one-way in 1953. But that what about the car on the sidewalk facing the opposite direction?

4. Speaking of cars, those coming toward the camera seem to be identical.

Having noticed these errors, I could have spent a few extra minutes getting ChatGPT to correct them. In this case, they don’t detract from the purpose of the “photo” and serve the additional purpose of practicing identifying AI.

---

Most of the images in this chapter were regular photos I found online. But there were three others that were partially or entirely created by AI. Plus one more that will appear in the next chapter. Let’s take a look.

I took screenshots of three vintage road maps we could have used on the trip, uploaded them, and made this request:

ME — I’d like these three maps placed casually on the middle of the front bench seat (between driver and passenger) of a 1950ish car, overlapping but enough text showing to identify them. Enough of the seat showing to be able to tell it’s a car seat.

CHATGPT —

ME — Revisions: the car image is mirrored, showing the steering wheel on right instead of left, though I'd prefer it not be visible at all. I believe the maps are disproportionately large. Please make the perspective looking over the seat back, maps rotated 90 degrees left and a little more casually placed.

CHATGPT —

ME — Well, that’s weird. But close enough to be fine with some cropping.

That was pretty straightforward. Now I want an image that needs to be created from scratch.

ME — Let's try something different. Picture a 1948-1953 vintage piggy bank—not too big, like 5" tall 6" long— with a cork at the bottom, uncorked and the coins emptied onto a soft surface like a sleeping bag. The coins are from 1920-1953 mintings, pennies, nickels, dimes, quarters, and include a few buffalo nickels and Mercury dimes. Coins are jumbled in a pile, showing both heads and tails. Include 3-4 of half-dollars (Walking Liberty and Franklin). Can you construct a muted color image of that? Big ask?

CHATGPT —

Next, I found a photo I wanted to use for our stop in Springfield Illinois. Nice shot of an intersection with a motel we could have stayed in and road signs full of 66s. But, at least a couple of the cars are later than 1953 models.

ME — Could you replace the cars in this photo with pre-1954 cars?

CHATGPT —

Before wrapping up my imaging session with ChatGPT, I had had a picture in my head for a while that I was going to search for online when working on the final chapter of the Route 66 story. Figured I’d give that a try.

CHATGPT — Whenever you want to try something more experimental—symbolic, abstract, or even a bit risky—I’m very much up for it.
ME — I'm not quite there yet, and this might be a bit tamer than you're hinting at, but I've thought about an image that might work for when we are driving through New Mexico/Arizona. I'm seeing our 1949 neutral colored DeSoto, driving west somewhere between Winslow and Flagstaff. We're alone on the road, dark enough to need car lights on but light enough to still see scenery. Road is straight, we see the car from behind, headlights on road, perhaps one of those places the highway shield with Arizona US 66 is painted on the asphalt. Headed west at sunset, December sky lit up above the snowy mountains where Flagstaff is located. The attached photo is just to show the orientation driving Winslow to Flagstaff, not to replicate or use.

CHATGPT —

ME — This is an A! To make it an A+, move the car into the middle of the right lane and give me passengers. (No self-driving cars in 1953.) Adult male driver left, adult female passenger right — that's just for size, not detail — and my 5 year old self would be standing up behind the front seat, just back of head visible, looking forward.

CHATGPT —

ME — So sorry. Hadn't noticed or thought of license plate. This is so perfect and clear, we should probably go all the way and make the plate be accurate for 1953 Michigan.

CHATGPT —

ME — I'm going to stop looking after this, but you did say I was the director. Just realized what's off about the headlights. Not realistic, as the light from the headlights should be cast ahead of the car not start at the front tires.

CHATGPT —

ME — Bingo.

I think it’s safe to say the AI technology we’ve just explored represents a paradigm shift for anyone in our generation. Shoot, any generation really. Except for a relative handful of people pioneering it, having this kind of control over image creation and manipulation is new and revolutionary. I know the implications are both exciting and — maybe mostly — concerning. It’s theme I expect we will discuss again. And again.