International Ranger Day (212/365)

Chuck Norris died this past year. At first, I figured this day was some prankster nod to that actor’s stellar performance in Walker, Texas Ranger. Alas, it is more sensible than that; and sensible international days are quite rare in my estimation.

No, it’s not for my favorite character type in Dungeons & Dragons either – I always played a human ranger for some reason. Nor the Power Rangers…

Today we honor those park rangers around the world who have sacrificed their lives in the line of duty. Often, they die from occupational hazards. Many times – check out India! – they are killed by animals. Other times, they are killed by poachers. Well, I don’t have to explain it to you, because I created this map with a single prompt using a style guide and saying it should ignore the suggested theme background color and go with green. The style I used wasn’t even a mash-up. It was straight from the Prompt Cartography Map Design Lab – the city dashboard one or whatever.

And there it is… a very interactive dashboard that literally allows you to explore the dataset. I used the Web Mapper Spatial Dataset Make tool to compile the dataset for me from a bunch of disparate and hard to track PDFs online. Then uploaded it with the style and a single prompt and watched the Tigers lose in 12 innings to the Orioles before checking b ack and uploading this straight to the website.

Sure, an expert could quibble a little longer, but that’s not the point of a Map-a-Day competition. What I learned: not only do I never need to visit a data portal again;  I’ll never need to learn how to create a dashboard with GUI software again. And I use all the time gained to play card games and watch television.

Speaking of which… I should go hang out with my family. Enjoy International Ranger Day! Chuck Norris, RIP. 😉


View the Map Here


Web Mapper GPT Prompt

I am interested in creating a map to celebrate International Ranger Day – a day recognizing the sacrifices of park rangers that have died in the line of duty.

Can you please design a map – mobile first – showing the total number of ranger deaths per country, as well as year-by-year deaths as the user would like, and interactive charts that allow the maps to be filtered and re-symbolized based on cause of death, etc.

An interactive data exploration that pays respect to the deceased, sits above the fold in landscape mode, is designed to work with mobile first but is also designed to look good on desktop, and follows the attached style template – though colors can vary to match the theme of conservation rangers and national parks.

Please don’t waste a ton of space on a header, etc. Also, make sure that the mobile interfaces are easily accessible via a hamburger icon or slide-up, slide-out panel, not via large buttons on the maps, etc. Thanks!

 

International Friendship Day (211/365)

I absolutely love propaganda maps. I think they are effective for doing what every map does – making an argument about the environment.

Yes, I find some propaganda maps abhorrent – particularly the ones that fly in the face of my own beliefs. (Though, I’m still fascinated by them.) Others, I smile and applaud – because they are witty or really sticking it to belief systems or institutions I don’t much respect. And sometimes… Well, I really just enjoy making propaganda maps myself. Particularly based on classic propaganda maps that preceded them, in this case a World War II German one that I find quite effective.

So without further ado, here is today’s map celebrating International Day of Friendship.

It’s just a map making a visual argument about the world like any other. My perspective of the situation.


Map of US International Friendships, July 2026. Argentina, Israel, and Saudi Arabia are the only friends left. View map at full-scale here


ChatGPT Image Creator Prompt

Please create an official looking, CIA World Factbook-style looking map titled: United States International Friendships, July 2026 The map should have the US in the middle of the map in bright yellow.

It should be a rectangular map of the world, Mercator-esque projection. Every country in the world except Saudi Arabia, Israel, and Argentina should be colored in 95% black. The oceans should be 80% black. The country boundaries (internal, not on coastlines, i.e., islands won’t have any boundaries) should be 80% black too (same color as the ocean fill.

I’ve attached an image to inspire how I would like this map to look. Do not include a page fold, though.

If you can add the same old school book texture, that would be great!

Also, the title should be at the bottom, and please include a solid neatline – would be great. Label the countries that are friends. The US should be yellow too.

In the lower right, please put a free to distribute, reuse, and modify with attribution CC abbreviation (I don’t know what that one is, exactly, e.g., CC-BY-NY-BYOB ;-)) with attribution to “Ian Oas”. Thanks!

The Odyssey to see The Odyssey (extra/365)

I just sat down at home to eat lunch. I was reading a short article online about the technology behind Christopher Nolan’s ‘The Odyssey’, specifically that he shot it on 70mm IMAX film, and that there are only 41 theatres in the entire world that have a 70mm IMAX film projector capable of showing the film in its intended format. There are 25 of these theatres in the US. I wondered where they were. I only had my cellphone to hand.

I asked CoPilot to search for the 25 movie theatres in the US that have 70mm IMAX projectors showing The Odyssey. I asked it to build a georeferenced spreadsheet of the name of each theatre, the State it was in, and the latitude and longitude of the theatre.

I took a bite of lunch (homemade chilli if you’re interested).

I then asked ChatGPT to create a reference map from the georeferenced spreadsheet, prioritising accuracy. It created the following map. Functional. Accurate. Un-styled.

Odyssey reference

I then asked it to use that map as the input, check its workings, and style it cinematically, and using imagery that would befit The Odyssey (without impinging any copyrighted material). And it gave me the following.

Odyssey

And now I know where the 25 movie theatres are in the US where I can see The Odyssey on 70mm IMAX film, and a map that I can share with others who are interested in that question. I have tickets to see the movie at my nearest 70mm film IMAX next week. Looking forward to it.

I finished my lunch and went back to work.

International Tiger Day (210/365)

They’ll likely kill you if you get too close but Tigers are beautiful, magnificent animals. They’re also seriously endangered with a number of sub-species already extinct. And that’s why International Tiger Day exists to bring focus to conservation efforts and the plight of these big cats. In a twist you likely won’t see coming, the day was created by a certain Russian President Vladimir Putin at a summit on Tiger conservation held in St. Petersburg in 2010. Putin has made it a mission to save the Amur Tiger, and one of the outcomes of the summit was to impose into law punishments and prison sentences for poaching, illegal trade and transportation of Tigers.

In support of International Tiger Day, here’s a map of the general former and current Tiger habitat for the nine identified sub-species. ChatGPT did a pretty good job which I verified against other, published maps. Labelling has improved significantly compared to what it was capable of earlier in the year, and our series of maps. What I like about what this map shows is that the same image generator can produce a VERY different aesthetic from, for example, yesterday’s Water Park map. This is largely down to the human input of crafting a prompt that directs the LLM to make the map within constrained guidelines. The point here, is if you, the human in the loop, know what you want, then you remain in control of the output. You are designing the map in your mind’s eye, and are asking AI to execute your plan.

Don’t lose your stripes if you’re perma-offended.

Tigers

Original Prompt (ChatGPT)

I’d like you to make a map of Asia that illustrates the former, and current extent of territories of Tiger habitat. The Tiger is a single species but the map should illustrate the range of the nine sub-species namely the Bali (extinct), Sumatran, Javan (extinct), South China, Indochinese, Malayan, Bengal, Caspian (extinct), and Siberian (Amur) Tigers. Current habitat should be in a darker hue than the former habitat and different hues used for different sub-species so it’s possible to differentiate the different ranges on the map. I’d also like you to be careful about how you shade each hue on the map. There should be no internal variation in each hue. It needs to be a block colour rather than looking like a watercolour. Please include illustrations of the different tigers, identifying how they differ, and with an indication of the number of each sub-species currently estimated in the wild. Add source notes to the bottom of the map to indicate where your numbers were found. Feel free to include the Latin name for each sub-species. I would like the background of the map to show landmasses in light grey, and water as a lighter grey. In other words, a neutral backdrop should help the reader focus on the thematic content. Please add a title ‘Tiger Habitat Range’. There’s no need for north points or scale bars so please omit.

National Water Park Day (209/365)

While some online folks are arguing amongst themselves about the value of our little AI mapping experiment, continuing to label us as ‘slopmerchants’, AI proponents, and determining that we are incapable of understanding and accepting critique I thought I’d reiterate a few comments we’ve made elsewhere but which seem to have gone unheard.

If you begin your so-called critique threads with a statement such as “I don’t like AI maps” then proceed to simply say you don’t like what we’re doing you’re not actually offering anything useful. If you add personal and derogatory assessments of us, and our motives to that, you’re not helping move the discussion forward at all. In reality you’re starting an argument, then framing us, and our work in pejorative terms while continuing to try and provoke a response. As we’ve said many times, we’re simply not going to engage. We’ll be reporting our findings, what works, what hasn’t worked very well, where AI (and us, as operators) have failed, what works for cartography, what perhaps doesn’t (yet?) in good time. That’s the aim. That’s the point. That’s always been the point. And in that mix we’re now also likely to comment on the way in which people’s reactions to this project have verged on the intolerable at times. It’s been an emerging issue which is going to be important to reflect upon.

Today’s map is made using Generative AI because it’s a pictorial, or illustrative, map. I am fond of illustrative maps so I naturally gravitate towards this style. In looking around my home right now as I write this I can see Jasper John’s ‘Map’, Jo Mora’s ‘Yosemite’, Hal Shelton’s ‘Colorado – Ski Country’, The Tate Gallery ‘Tube by Tate’, James Niehues’ Ski trail maps, Stephen Walter’s ‘The Island’, Ruth Taylor’s ‘California’, MacDonald Gill’s ‘Wonderground’ map, Anton Thomas’ ‘Portrait of a Continent’ and ‘Wild World’ and many others. This style of cartography is not to everyone’s taste of course. But as a cartographer, when I see a theme entitled ‘Water Park Day’ I am naturally inclined to imagine a landscape where the map is a fun landscape surrounded by water in which characters are having fun. This is not much different to how Jo Mora envisaged the landscapes he drew. The difference is that I’m experimenting with Generative AI to assist me with the production of an artistic map. I can draw (though certainly not as well as Mora), and I’ve shared some of my hand-drawn maps before. But let’s say I don’t have weeks to put the map together, and maybe one can imagine a client demanding a map in very short order. In that sense, and for this purpose, Generative AI provides an opportunity. I don’t have copies of Tolkien’s maps but one could imagine him experimenting with AI to build his landscapes, and I’m sure many contemporary map-makers of fictional places are also doing so.

One criticism of this has been that this sort of art is derivative. Well, yes, to an extent, but so is most art. As humans we see things, and we build on the inspiration. This is really all an LLM is doing. I know people who openly admit nothing they do in their map-making is original and that they copy everything from somewhere. Yet they produce good work that is attractive, and widely praised. If creating work so derivatively is such a heinous crime then such people should be out of a job rather than being praised right? Instead, people turn a blind eye to some people’s practices, but if it involves AI, then that’s roundly criticised. Isn’t that double-standards? Other people in the industry are also using AI but they’re not admitting it, or explaining what parts of their work rely on AI. Maybe that’s where Ian and I have gone wrong in being totally up front about this particular project. We’ll never know. Though it is fascinating to see how some are evolving their work and using AI under the radar without any criticism.

Another criticism is that this will undoubtedly kill the careers of illustrators, and of cartographers, perhaps. Hasn’t this been an accusation of every technological shift in history? Again, some folks may find their ability to attract commissions is reduced. Or maybe they can harness AI in ways that they find acceptable and useful to assist in their design and production? Perhaps this is by training AI to understand their unique style and have the AI return work that mimics that style. This already occurs for the written word, but maybe Generative AI illustrations will develop in this way too. Ian has developed a lot of styles over the past few weeks and I intend to play with these a little more.

So, today’s map is a playful, illustrative map that imagines the world map as a water park. Generative AI is pretty good at these sort of highly saturated imaginary depictions. There’s plenty of maps from across the last few decades that take a similar approach. In particular, maps designed for children with bright colours, and lots of playful detail. They’re not trying to be serious. Just colourful fun. Nothing more. Nothing less. It’s designed to bring joy. Sometimes that’s all a map needs to do, and I like those sort of maps because I’ve made some of these by hand before too (remember Trump’s Ties?). I could have iterated the map more. I’m getting a little tired of these maps all having curved titles centred at the top. They sometimes look very similar but hey, if that’s a ChatGPT style, then that’s something recognisable right?

I hope you like today’s map too, but if not, that’s OK. It isn’t a reason to have a meltdown. Just move on, and save your judgment for when we bring our little experiment to a close and offer our reflections. And in the meantime remember the park rules – Be Kind, Stay Safe, Drink Water, and have Fun!

water parks

Original prompt (ChatGPT)

I’d like you to make a map for water park day, perhaps a world map depicted as a water park. It should be brightly coloured, with rushing water, and endless excitement filling the air. It needs to exude the joy of cooling off in a place designed for pure fun. Please include towering slides send riders speeding down into sparkling pools, with lazy rivers offering a gentle drift under the sun. Every splash, laugh, and thrilling drop makes these parks a favorite getaway for families and friends and reminds everyone of the happiness waterparks bring. They provide a break from daily stress, offering both adventure and relaxation. High-speed rides challenge the daring, while calm pools invite visitors to unwind. Please dive headlong into this mapping project!

Norfolk Day (208/365)

Another day, another map. It’s Norfolk Day. If you peruse mostly tourist-trap stores around the UK you’ll almost certainly see tea towels designed as if ChatGPT had made them, but several decades ago. They’re heavily pictorial, and often show historical places, flora, fauna, people and anything linked to the county (or region). So I asked ChatGPT to make a tea towel in respect of the county of Norfolk in East Anglia, UK.

More generally, while it’s another week of making maps in this experiment the online noise about it continues by those who are upset about it. To reiterate – critique is perfectly fine and encouraged but we’re not engaging with people who call what we’re doing professionally negligent, unethical, or who lazily charecterise our experiment as ‘slop’ of some type. It’s noise. It’s unhelpful, and abusive. It’s not critique. Further, the notion of changing what we’re doing because, 7 months in, someone would like it done a different way is not really how experiments work. Please afford us the courtesy to finish what we are doing and have reported on it. While we acknowledge some very helpful comments by some, we would encourage the vocal minority to explore their own experiments in using AI in ways they find acceptable.

Norfolk

Original Prompt (ChatGPT)

Please make a map of Norfolk, UK to celebrate Norfolk Day. Please imbue the map with points of historical note that a casual reader may find interesting. Clearly the underlying geography must be accurate so I encourage you to check with published topographical maps of the region. I’d like you to style it in a similar way to the long history of depicting historical maps on tea towels in support of UK tourism. And just because I want you to show you can make errors that people will find fault with, please make sure you include a picture of a fish with two tails, one at either end.

All or Nothing Day (207/365)

Forgive the lack of effort today (or don’t, I don’t particularly care) but I’m sat on my sofa, it’s 4:25pm on a Saturday, it’s 105°F outside, and I haven’t made a map for tomorrow’s post in this apparently divisive series. So I thought I’d just see if I can make a map using AI on my phone. And the day’s theme worked well for a cheesy, throwaway map-gag that’s been made before such as by Lewis Carroll in “The Hunting of the Snark”. Maybe the LLM has read it? I didn’t prompt it in this direction but it went there anyway.

Is it a map? Well, it’s got a border, title, subtitle, legend, scale bar, and ridiculous north arrow. Nice layout. Well designed.

It’s now 4:39pm. Job done. Not great. Possibly not even good. But maybe it raises a small smile from one or two people in passing. And frankly, that’ll do me. Enjoy the rest of your day, and seize what you can!

Nothing

Original Prompt (ChatGPT)

In celebration of ‘All or nothing’ day I’d like to see you create a map that literally shows nothing. The day itself is designed to encourage people to seize the day (Carpe Diem!) and for them to perhaps do things they may have been fearful of doing. The implication is they will end up with all, or nothing. But they will have tried. So what happens if the map I ask you to make is the exact opposite of every other map I make… It shows nothing. I’ve never tried that before.

National Wine and Cheese Day (206/365)

Disruption often comes with a price. Over the last few weeks there’s been an extremely vocal online community writing inflammatory social media posts and misrepresentative blogs about the AI mapping experiment Ian and I have been undertaking. It’s like Lord of the Flies: The Cartography Years. Despite many more interested people (note – not necessarily positive, but open-minded) than not, there has to come a point where our side-project, done on our own time, becomes simply not worth it.

For decades, Cartography has faced numerous technological changes. The International Cartographic Association uses ‘Commissions’ as key instruments to explore how all manner of disruptions and developments might impact the domain. From work that people do, ICA brings forward ideas, and frameworks which help define cartography as it moves forward and reacts to change. Does it always work? No. Can you work outside of ICA and still offer critical ideas? Of course! Ian and I have been Chair and Co-Chair of the Commission on Map Design for the last 16 years (we flipped roles half-way through). It’s provided an avenue for work in the broad area of the design of maps that gives it some visibility beyond self-promotion. It engages an international body of professionals across the cartographic spectrum.

But we face a headache. At previous inflexion points of technological change Cartography has generally been slow to adopt or adapt. And then it’s almost too late. With the advent of AI, despite all its problems and concerns, we thought that a couple of fairly-seasoned experts jumping in to the mix to explore opportunities and difficulties might help us get ahead of the curve. We perhaps naively thought people would back the efforts we were making to at least try things out. We did so without an agenda. We wanted to explore, and to experiment. The simple idea of creating a map a day was born, using the sometimes serious, and sometimes frivolous ‘Day of…’ lists we always see. It was a convenient framework, and one neither of us had any particular reason to be biased about.

For several months at the start of the year it was difficult. The maps were tough to make. Generative AI was making some really bad mistakes, and web mapping was a challenge. But slowly AI Assistants have improved across the year and our ability to write prompts that do a better job of controlling the LLMs also improved. And just as we’ve been finding our feet along came the online backlash. No names, but the noise has become almost intolerable. We’re finding we have to defend very innocent motives from people IN the cartographic community who are making gross assumptions about our intent. Now, I get that folks will have opinions. But most are asserting those opinions purely based on the fact they “don’t like AI” (or similar), and if they can’t think of anything about the technology to moan about then they just don’t like our ‘tone’. That’s not really how science evolves. But since academic publishing is largely irrelevant any more, and codes of conduct make conferences an impossible forum for sensible debate, then blogs and social media is what we’re left with.

So, what to do… carry on regardless, with significantly decreased appetite, and either ignore or continue to bat away the haters (while trying to siphon out useful, mature critique). Or just end the experiment early. What is best for Ken and Ian? What is best for cartography? Are those two things the same? With upcoming conference presentations on the horizon we have commitments. And we’ve long-promised to report on what we find in our experiment to the wider community. But some already have us down as AI promoters so it’s largely pointless. They’re going to come to a conference presentation armed for a public take-down (except they won’t be able to do that due to the codes of conduct they were probably involved in writing in the first place). Ending a presentation by saying that voices from inside the community itself made it impossible to move forwards seems to me it would shine a very dim light on the way we act as a professional community. Let’s not wait until researchers have given us their conclusions, let’s shoot them down early, and often, instead! If no-one is interested in what we might have to say then the community has spoken, and we can just get on with doing other things. If there’s no interest in how AI might impact cartography based on a year’s worth of trying out what it has to offer then fine. That seems awfully narrow-minded to me but I could be wrong. What I do know is this experiment has eaten considerably into mine and Ian’s lives over the last 6+ months. Neither of us needed to do it. But having people so vocally shout-down our efforts has been surprising.

We haven’t made our minds up just yet because we believe what we’re trying to do has value for the wider community. We may even end up revealing that AI is a piece of crap for making maps. But that would be pre-empting even our own conversations and findings. It would be deeply frustrating to ditch this work just because of a few rather thoughtless souls but it does tend to be the case that the few always tends to spoil things for the many in most walks of life. Maybe this is just one of those occasions and we just have to shrug our shoulders and live with it.

So – if these blogs just end, or the posts on X, BlueSky, and LinkedIn fall silent you’ll know what happened. We just gave up, and gave in. If they continue then we’ll have persuaded each other that, for now at least, it’s worth trying to cut through the crap for a bigger end goal.

So…for now, here’s today’s map. It might be the last in our series. I don’t yet know.

A few years ago I made a wooden cheese board, and filled it with geographically appropriate cheeses that I served to a room full of geogeeks in London. It was a great, and tasty, success. I thought today I would try and prompt our AI map assistant to create a digital version.

Here’s the real-world version. Real wood. Real cheese. Taken with a real camera (with real sensors that captured the picture and converted them into glorious pixels)

cheesy

Although far less tasty it’s also way more easily produced in a matter of minutes, costs significantly less (there was over $500 of cheese on the original), and is far easier to share. But even though what I’m sharing today is no more than pixels, much like the photograph above, yeah – I prefer the original. I like maps. But I like cheese more.

cheesy 2

Original Prompt (ChatGPT)

A few years ago I hand made a cheeseboard in the style of a map of the United Kingdom. I then purchased different cheeses from different parts of the UK which I served on the cheeseboard to a room of geographers. It was a huge success. Could you create a digital replica of a cheeseboard of the UK with cheeses from across the map, positioned close to their origin of production. please label the cheeses (accurately and without spelling errors or hallucinations). Since cheese is most often paired with a fine wine please also show a glass or two of wine with the bottle and a playful label indicating fine taste in geographical wit.

National Amelia Earhart Day (205/365)

Mysteries always leave us with great stories. They take on a life of their own as we struggle to make sense of the senseless, or the logic of the illogical. History is filled with stories of adventure with endings that perhaps capture the imagination more than if everything had gone to plan.

Maybe that’s the case with American aviator Amelia Earhart. Earhart was a pioneer and counted many firsts in her lifetime but she went missing on July 2nd 1937 while attempting the world’s first circumnavigation by a female pilot. To date the wreckage of her plane, and her remains, have not been found despite many searches. This has ultimately led to all manner of stories and speculation about her final resting place and what actually went wrong. But like most mysteries we’ll likely never know.

So, for today’s prompt-built map I wanted the 1937 route showing the stops. I wanted it in a mid-1900s style but because I know AI sometimes struggles a little with precise locations and labels I’m going to do this in two parts because route accuracy is paramount. Firstly, I gave ChatGPT a list of places for the stops (via a web site) and told it to create an accurate route map, which it did. Then I asked it to style the map it had created in a mid-century adventure map style. I also wanted to riff on a joke that my good friend Nathan Shephard tells that if only she hadn’t used a Robinson Projection she wouldn’t have fallen off the edge of the map. A lovely map projection flat-earth joke thrown into the mix!

Pretty decent results I think. Sure, we can be critical of the pointless north arrow compass rose but it adds to the aesthetic in this instance. Take it off if you want. I left it on. My decision.

Amelia map 2

Original Prompt (ChatGPT) Part 1
Could you make a map of the world using a Robinson projection that plots the route of the final flight of aviator Amelia Earhart. Please use the details at this web site to accurately position the stops she made along the route https://tighar.org/Projects/Earhart/Archives/MapsandPhotos/maps/worldflight.html

Amelia map 1

Original Prompt (ChatGPT) Part 2
Great! The route is accurate. Now, using that map as a basic structure I’d like you to re-style it to evoke the mid 1900s explorer style maps that you might see in an Indiana Jones movie. The route and stops Earhart made must remain accurate in terms of the actual route she took, and also the location on the map where you position the stops (I will be checking them again!) I’d also like to include a geographical joke and have it appear that Earhart literally dropped off the edge of the world, to be revealed as a flat earther, which is why the wreckage of her plane has never been found.

Vanilla Ice Cream Day (204/365)

Everyone’s a critic baby, that’s the truth
Everyone’s a critic baby, that’s no lie

Wait – I just stole a lyric from Hot Chocolate. And modified it. Is that allowed? Whose permission am I asking? I’m sat writing this listening to the new Rolling Stones album. It’s actually pretty good, in my opinion. I’m sure plenty think it’s crap. That’s their opinion. And we’re all entitled to express opinions, until others decide we’re not.

I want to tell you a short story. Rewind to B.C. (Before Covid). I’ve been an educator my entire career. I’ve taught many people who then spread their wings and off they go to do their work in their way and forge new careers. It’s incredibly gratifying to help people learn. And as part of my professional responsibility I always kept in mind a Royal Society demand to call out where we saw people making mistakes in our professional domains in order to maintain standards and to support knowledge transfer. I have some level of knowledge, and experience, and felt able to use my position to carry a flag for basic standards in the way maps were designed as conduits for communicating a message. This was almost always in seeing scientific errors as opposed to the aesthetics of design. And I felt social media was a suitable place to engage with the community back when it was some sort of community.

Except the community (or some parts of it) felt otherwise. I was seen as wholly and solely responsible for using a hashtag to brand maps I saw as falling technically short of my personal ideals. Worse, the incorrect assumption was made that critique of a map somehow meant being critical about its author. And my, did I get cancelled over it. I don’t wish to rake over these coals but there’s no debating with those kinds of people. In trying to do my best in support of my profession, others felt that public critique of publicly shared maps was inappropriate, unwarranted, and damaging. They also had issues with the style I sometimes took. Understandable – we’re all different. But let me be clear – this wasn’t everyone and despite pointing to many who found my comments helpful, informative, and useful I relented. So you don’t see me bother any more. Cancelled by a community with a few vocal people who put me in their sights and literally shot down my efforts because they took a dislike. A lot of their distaste became pretty vitriolic too. I’m not going to name names but I’ve largely avoided these people over the last few years.

But I’ve been forced to revisit some of this recently.

This mapping experiment that Ian and I are engaged in has lit a fuse with some. On the one hand we’ve received many positive comments of support for what we’re doing in exploring the use of AI in cartography. Again, no names but some very prominent people in the industry as well as folks we’ve never met who are following with interest. Academics have expressed their shifting perspective. Folks in senior corporate roles have taken an interest. But… there’s also been a backlash, and what should be a mapping experiment has somehow become a social commentary on our behaviour. We’ve been referred to as ‘professionally negligent’, accused of simply creating ‘AISlop’ and ‘PromptSlop’, characterised as ‘AI promoters’ advocating for a technology that will likely ‘put folks out of work’, being ‘unethical’, ‘uncritical’, being ‘sinful’, making ‘shit maps’ (also ‘dogshit maps’) etc. You get the gist. Some have offered thoughtful and engaging ideas because neither Ian or I have ever set about saying we’ve figured this out. The only truth is that this is a huge technological change we’re all going to have to deal with and we’re experimenting with what it might mean for our professional domain with open minds.

But people continue to want detailed expositions to their particular criticisms in a few characters in a social media post, or they want us to do this, and that, in a way that they individually find useful as if it’s the first conversation we’ve ever had with people on the subject. Then, if you do write down something long-form we’re told tl;dr (probably much like this blog post I suspect)  We’ve recorded podcasts, written blogs and essays, developed new web sites, written a forthcoming book, are running a workshop at a forthcoming conference, have upcoming conference presentations on the horizon, have developed schemas, AI Assistants, and tried our best to reassure people that when we’re done with our 365 maps we’ll be trying our best to pull together our experiences; to figure out some best practices as things currently stand; and to share what we’ve learnt. What more do you want?

But some have already decided on where they draw the line with AI in cartography. For them it seems they liken it more to a social movement than the inevitable juggernaut of technological change that is going to happen happening. Their mind is made up, and they’re happy to express that opinion and use our efforts as irrefutable evidence they’re right. They also seem uninterested in the materials we’ve built across the year so far, preferring simply to pick on a map or two and tell us a border or label is incorrect. Seriously – there’s just no pleasing people. I could probably point out errors on most maps, made by most people, using most tools (except I can’t because I’ll get cancelled again). To the Tower! It’s tiring to have to constantly re-tread discussion when people can’t or won’t do some basic research and find out what we’ve already said on the topic. To date there’s 204 maps with associated blogs. Sometimes we’re rather busy with other demands on our time so it’s a brief, quick and dirty map. Other times the maps and thought that has gone into them are more involved. Much like all maps. Right? But – be damned AI cartography! If you want to think of our experiment in terms of client demands then the client has asked for one map, per day of the year, built using AI, each one on a theme relevant to International or National ‘Days of…’. They haven’t said ‘create a great map’, or even a ‘good map’. Just ‘create a map’. Much like an awful lot of clients I’ve come across over the years.

So let’s reiterate our motive – it’s an experiment. We’re creating maps every day for a year using AI as a major (or sole) tool in the workflow. We are directing AI agents that are publicly available or that we’ve built (well, Ian’s built!) to use LLMs to create maps. These are sometimes images using generative AI, or vector-based interactive web maps. We are directing the AI much like a Director frames the story but lets the camera crew, lighting, set designers and actors get on with interpreting the direction and delivering ‘an’ outcome. Producers and sound engineers do the same in a recording studio. Chefs do the same in a kitchen. Every creative endeavor results in an outcome which some folks will like, and others won’t. Monet? Constable? van Gogh? Hockney? Jackson Pollock? Banksy? All creative but in different ways. Every map is only one possible outcome of many different possibilities regardless of who made it or how it was made (said someone once, famously). For many, technology has all too often limited what we could achieve. The number of times I’ve envisaged something in my head but not been able to deliver it because of some technical limitation or other is a very long list indeed. And every time a big technological change impacts cartography it is ALWAYS one step forward and two steps backwards. New people jump on board because something new captures their creative imagination and they are skilled in the new tool. Whatever benefits are brought about are always offset by limitations that take time to come up to speed. So we could sit around moaning – or give things a go. We chose the latter path.

So, what of the maps? The design is largely under our control through our prompts. Sometimes we iterate if we spot errors. Other times we don’t because part of this experiment is not to simply say “hey – AI is great”. We explicitly want the examples that have performed less than we would like. It helps establish what’s working, what’s not working, and how similar prompts might yield different results as time passes and improvements are made.. Much like many others do with their maps made with whatever tools they use, they publish maps that may contain errors. Caveat Emptor! Sure, some are sloppy, but they are not ‘slop’ simply by virtue of being made using AI technology. That’s such a lazy characterisation. Sloppy maps have always existed regardless of author or technology used in design and production. But increasingly we’re getting pelters from the very community that called me out for trying to call out sub-standard web maps when web mapping, and coded maps were becoming ubiquitous, and often made by people with little background in making maps (often resulting in the naive errors that were abound). Some people think I should adhere to higher standards, or not get involved at all. I see that as a dereliction of duty. Why shouldn’t we get involved in such a major transformative change? I mean, I don’t really want to retire just yet so I probably ought to think about how I might navigate things going forward. But I’m learning through practice. I’m literally getting my hands dirty (read the original editorial for Issue 1 of the journal Applied Geography by my old PhD Supervisor), and stepping way outside my comfort zone. I’ve talked about this before – particularly in relation to attending conferences outside of the normal cartography ones to meet new people, share map knowledge, and learn from others in allied domains. It’s fulfilling, refreshing, and devoid of the boring perpetual inward looking discussions that have been going round and round for years.

Wait a minute – so the very same people who found my efforts at maintaining cartographic standards at the dawn of the last major technological innovation abhorrent are now directing their ire at me for giving this latest technology a go? I’m messing about with it as an early adopter. I don’t have the answers. But clearly I’ve transgressed a line in the sand that some find fundamentally objectional. They’re applying a premeditated bias on what Ian and I are doing based on the tool we’re using, and then, by inference, characterising our motive. They’re immovable. It’s an incredibly closed-mindset. They’re happy to call it out on social media too. They’ve become experts at the passive aggressive post or blog that hints at a wider discourse but never names names or provides any real evidence to support their beliefs. They sometimes dress it up as an ethical debate, or some sort of insider-threat, or doing the work of the devil in fulfilling the work of billionaire sci-fi organisations as they seek to control all that we do. I’m comfortable with my ethical approach. I’m open and honest to the point it sometimes gets me into difficulties. I’m not trying to hide in plain sight.

I’m guessing many of these folks are oblivious to the deep irony this exhibits. This is the exact same behaviour I was profoundly criticised for only a few years ago. What happened to the live and let live philosophy? What happened to protecting the map-maker and their right to make the map they want using the tools they want? What happened to giving them a safe, uncritical space in which to experiment and contribute? What happened to letting people finish what they’ve started before piling on? I’m truly amazed how rapidly some people have pivoted. People who framed my entire career as ‘roasting people’ are now happily deriding this little side-project that I’m involved with. Accusing me of claiming a moral or ethical high ground by demeaning others is now exactly what some of these folks are doing. That’s really quite something. As Rush would suggest – Time Stand Still.

I’ve long given up trying to have a discussion with these sort of folks on social media. It always just deteriorates. But I’m going to stop engaging entirely. It’s pointless noise because they offer nothing constructive. If you don’t like what we’re doing, maybe try your own experiments and contribute? Or maybe do something that supports your assertions. You may very well be right, and it may well be that Ian and I have got this horribly wrong. But prove it rather than just parrot the usual lazy critiques. And in the wider world, is Mick Jagger wrong? Is George Lucas wrong? Is Dua Lipa’s producer Ian Kirkpatrick wrong? Should we ban Ed Sheeran from using loop pedals? Maybe anyone who DJs using a Mac Air should be banned? And heaven forbid we ban drum machines. All have embraced technological innovations that have impacted the creative sphere in music or film, and have worked with it to their advantage rather than sit back and moan about it. Good enough for them to try new stuff out, but as with so many technological shifts in the past cartographers seem very happy to sit in their echo chambers and complain about change. I’ve seen it so many times. I’m reminded of the story of a prominent UK cartographer who was militant in expressing dissatisfaction at GIS becoming a useful tool in cartography, and how web maps were useless, and Google Maps wouldn’t last. They stuck with Macromedia Freehand. They soon had to retire. It’s sad. They were talented and had much to offer, but technology rapidly overtook them and their business. I genuinely encourage people with a distaste for this experiment to go and do their own work. Prove we’re wrong. That’s how to engage – not just criticise on social media using approaches, and personally targeted comments, you used to apparently be wholly against anyway. You literally cannot have it both ways.

So, every avenue in life and is impacted by technology. Does anyone want to give up their microwave oven? Electronic toothbrush? Cellphone? Cartography is an art, science, and technology. I’ve lived through the transition from pens and darkroom tech, through desktop publishing, and into GIS; from mainframe, to desktop, to mobile and the cloud. AI is next. What it’s currently good at, and bad at, where we are, and where it’s going as a community eventually draw the line in the sand is up for debate. And I do mean debate, not intransigence if you simply don’t particularly like what we (or anyone for that matter) are doing with it. So, I apologise if you find I no longer engage, and I also apologise to the few folks who have merely questioned, and offered perspectives. They have been acknowledged (I hope), and I truly hope you know this expression of frustration is not in any way aimed at you. I fully welcome mature interest in our experiment, but everyone, please remember this is a side-project. By necessity it has limits in what time we can devote to it, it’s not part of our day jobs, and we have no funding. Maybe just be a little nicer?

I nearly forgot – one last quick point I wanted to make was that some have (for good reason which they have explained) asked us to mark these maps as ‘Made with AI’ or similar. I understand why but we haven’t mainly because they exist firmly within the reference frame of our blog posts and social media posts that express that they are part of a specific project. In and of itself that has become a short-cut to dissatisfaction for some anyway, which is something we wanted to avoid by not badging them. I don’t badge work that I make elsewhere as ‘made with GIS’, even though that’s pretty obvious too.  I rarely, if ever, see maps badged with their mode of production. Why should we brand maps that use AI? It’s as if it gives people immediate and uncritical permission to pile on. The interesting fact is that I also use AI in my day job as part of the workflow of designing and producing maps. Not one person has spotted this, called it out, or objected to it. I’m not even going to tell you on what map I last used it, but I can tell you it likely saved me an entire day of effort which I could then spend on other tasks. Now, isn’t that a nice saving you can enjoy, or pass onto your client?

So, onto today’s map made using AI – it’s Vanilla Ice Cream Day. It’s also Sprinkles Day. The two go hand in hand. Depending on your perspective, what follows is either an entertaining pictorial map, rendered as a pixel infused image that I asked the AI to make using clear directions. Or, it’s the very worst of generative AI slop because you have an objection to the fact I didn’t make it using Illustrator or GIS and the word slop is conveniently derogatory. If the latter – good luck making something as trivial and fun in less than 1 minute 38 seconds. Trivial and fun is as much part of cartography as serious and informative. Different strokes for different folks. It’s a hell of a stretch to suggest one is ethical and the other isn’t. And before you suggest this map is un-editable well, it is. Photoshop would help with that (other pixel editing programs exist), and in case you’d forgotten, we’ve been dealing with raster data in GIS for half a century.

Oh – and let me save you the effort if you plan on trying to figure out if I used AI to help write this. I didn’t….but I could have, and that’s the beauty. Use it for what works for you. Its ability to help in many different ways in our day-to-day work is only going to evolve further and keeping an open-mind on the possibilities it might bring is surely a healthy mindset. But enjoy trying to stoke faux arguments, and rivalries if you want – AI is here to stay but no-one debates all of the tech changes that have gone before (jeesz, who recalls the fights at the famous copperplate engraving conference when the lithographers showed up!) so this will also pass and it’ll be something else that comes along that people get fundamentally upset by. I’ll have a “99 flake” thanks, with a cherry on top.

Vanilla Ica Cream

Original Prompt (ChatGPT)

Hi. I am looking to make an illustrative (pictorial) map in celebration of Vanilla Ice Cream Day. I would like the map to show continents as tubs of ice cream containing scoops of different flavours but as it’s Vanilla Ica Cream Day there needs to be a focus on this particular classic flavour. I would like the map to be covered in sauce and other ice cream related delights. Importantly, it’s also sprinkles day on the same day so the map needs to be covered in sprinkles of all types. Add chunks of fudge, candy, and whatever to make this a delectible dessert map. Finally – we’re aware of some criticism of the maps you’ve made in the past so make this good. Keep errors to a minimum, no hallucinations. This has to be top notch! And just for the British contingent, please include a ’99 flake’. Thanks.