Prompting the Norway Story

After I got home from Norway, I started using ChatGPT to get my head around some of the family history we'd discussed on the trip. My mom and I had dedicated part of our time there to visiting relatives and learning more about our genealogy. I was making a few one-off pages about the families and the farms we'd visited.

At the same time, I was playing around with image prompts based on photographs I'd taken on the trip, trying them in different styles. Some paired photographs with pencil drawings. Others made the pictures fade into paper. From there, I got curious about building a little scrapbook from my photographs.

I already had quite a bit of information to start from. This was one of the first trips where I'd used ChatGPT more heavily to plan routes, partly around weather conditions and car charging locations. I'd kept making decisions in that same conversation along the way.

I asked ChatGPT to summarize where we'd actually gone, which gave me a day-by-day account of the trip. I brought that into Codex with my photographs and the details I remembered. I wanted the Norway story to follow the drive, with a path that moved through the places we'd visited and paused at the photographs.

I've included some of my prompts and Codex's replies on the left, alongside the parts of the story they relate to.

First, I started honing in on the design. Codex generated three concepts, and I chose the field journal shown at the top of this post. I liked the paper, the pencil drawings, and the red path through the photographs.

My approach was to generate concept art, choose a direction, and refine it before building the working version. Sometimes I wanted to combine parts of two concepts. I kept using that approach as I added more to the site.

We started with one day so I could see how it worked. Once I had something I could scroll through, I wanted to keep going and bring in the rest of the trip.

I had a day-by-day summary of the trip, and we could fill in some of the gaps using the EXIF metadata from my photographs. The dates helped put the photographs in order, and the location information helped place some of our stops on the map.

I brought in my Hasselblad film photographs too, using what I remembered from the trip to work out where they fit. The finished album has 125 photographs.

I kept adding context about the people in the pictures, the farms we'd visited, and the family connections we'd talked about. I also had to go back through the earlier conversation and sort out which places we'd actually visited and which we'd only planned to see.

Once I had the photographs and the account of the trip together, I started wondering what else we could bring into the scrapbook. I began pushing Codex to find road data, drawings, and videos of the places we'd visited.

The path was one of the first things I kept pushing. At Trollstigen, the switchback road, I liked the idea of following it up a sketched model of the mountain.

Initially, it was just a generic path. I started giving Codex map screenshots and asking it to get the actual road and location data. I wanted it to follow the bends we'd driven.

For Trollstigen, I pushed it to get real topographic data too. I wanted to keep the drawing style, but have the mountain and the road based on the actual place. I kept refining the concept and the working version from there.

Codex found the road line from Norway's road authority and elevation data from Kartverket, the national mapping agency. It used those to build the hillside and place the road on it.

These figures were made for this post from the saved website data. The measured heights gave us something to check the generated concept against as we refined it.

By the time I got to the part of the trip where I rode a wheelbob at the Lillehammer Olympic track at Hunderfossen, I wanted to try something more interactive. A wheelbob is a bobsled on wheels for the summer season. I'd also done competitive bobsledding.

I asked Codex to find the actual track data. I figured there had to be something available from the Olympics that we could use. I wanted to follow the course just behind the sled as I scrolled. The first concepts were too realistic, so I pushed it to keep our sketching style.

I chose the rougher charcoal direction. Once we had a moving version, I gave Codex photographs of the sled and a YouTube video of the ride. It went through the footage frame by frame to compare it with the model.

The video showed details we were missing, including a flat floor and higher walls with sharper edges. Near the end, one bend also seemed to lean the wrong way. I thought the wall should be on the other side.

Codex checked the video against the model and found that the bank was reversed. I kept asking for the actual track drawings.

It found a 1993 site plan and the operator's map. Those helped us check the bends. We still didn't have exact measurements for every bank, so the model remained a simplified version of the course.

From there, I kept refining the sled's cage, the track, and the movement. I'd look at the next version, point out what seemed wrong, and ask Codex to keep working on it.

That made me curious about how far I could take the other parts of the trip. For Hardanger Bridge, I wanted to start with a drawing of the tunnels and then move into the drive across the bridge. I asked for some concepts to explore that.

I liked the cutaway showing how the tunnels connected to the bridge, and I liked the view from the road. I asked Codex to combine them so we could move from the drawing into the crossing.

Once I was happy with that direction, we needed the real dimensions to build it. An earlier search hadn't found a suitable 3D model. I figured there had to be engineering drawings available somewhere, so I pushed Codex to look for those.

It found construction drawings in a public tender archive. They had measurements for the towers and the road deck, which gave us enough to build our own model. I kept the drawings beside the chat so we could compare them with what we were making.

I kept using the concept to guide how the crossing should feel, and the construction drawings to check the structure. With both, we could keep refining the model and the movement.

I'd visited Copenhagen on my own the day before the Norway trip. I wanted to show my climb around the outside of the tower at Vor Frelsers Kirke. After building the bridge, I figured we could find drawings to build the tower from too.

I gave Codex my photographs and asked for a sketch concept in the style of the other models.

I liked this direction, but the early working model looked like a cone with stairs attached. I kept pushing for better drawings so we could get the shape closer.

Codex found a measured drawing in the Danish National Museum's collection. It showed the eight-sided structure inside the winding staircase. Even with that, I kept getting a model that didn't look like the drawing.

I also tried asking ImageGen to make a clearer study of the proportions, using the photographs and drawings as references.

With GPT-5.6 Sol, I really couldn't get the model to be better. I kept giving it photographs, drawings, and feedback, but I couldn't get it where I wanted it.

Only when GPT-6 Astra came out could I actually get a better 3D model. Astra was much better at 3D modeling. I could keep refining the tower and get it closer to the photographs and the drawing.

For Cirkelbroen, I gave Codex a video showing the bridge from above. I wanted to see if we could make a drawing that moved as the bridge opened.

I liked this concept, but I wanted to check how the real bridge moved. I'd asked Codex to find architectural plans as well.

The open and closed drawings showed that two platforms stay still while three turn together. The generated concept had that wrong. We used the plans and the video to correct it when building the animation.

While I was working through all these ideas, I kept refining and editing my photographs, updating them in the site, and working on the copy. I went back through the family passages to explain the connections and correct the details. I also asked Codex to use my Darkroom page as a reference for how I write.

The cover took a few iterations too. We tried generated backgrounds with space for photographs, and I ended up putting the final photographic cover together myself.

What started as a little scrapbook kept giving me ideas for what to try next. Once the path could follow the real road, I wanted to see it on the mountain. Once we could build the bobsled track, I wanted to get the ride closer. I kept doing that with the bridges and the tower too.

A lot of the work was deciding what information to give Codex next. Sometimes it was another photograph or a correction from memory. Other times it was a video or a drawing with the measurements we'd been missing. I'd choose a direction, look at the result, and keep pushing it.

In the end, I was still editing photographs and working on the copy alongside all of that. The more context I gave it about the trip, and the more I pushed it to refine the details, the more the scrapbook came together.

If you're curious what all those API tokens cost, here's the breakdown for building the scrapbook. Tokens are the small chunks of text an AI reads and writes, including code and earlier messages.

I have a ChatGPT Pro 20x account, so I don't pay per token. The $821.43 estimate is what this text and code work would cost at the published pay-as-you-go API rates for Sol and Astra.