The Umbra is coming, and the Riverlands are no longer safe. Our family must flee to the City of Winter to find another home.
City of Winter is the spiritual sequel to Heart of the Deernicorn’s indie smash-hit1 Fall of Magic. While Fall had you accompany a mysterious magus across the continent to a land of magic, City instead deals with a family of refugees fleeing a mysterious force that’s sweeping the countryside, and how they cope with resettling in the eponymous city.
Thematically, I think City hits harder than Fall: there’s something smoothly inoffensive and detached about themes like magic dying, while the refugee narrative is something that feels a lot more real, even to those of us living in first-world countries who experience of war and displaced populations is second-hand at best.
But while the theme of the game may be more well-developed, it feels like City is let down by its mechanics. While new mechanics expand play beyond the standard band-of-adventurers trope laid down by Fall, the modifications that Deernicorn have made to the original mechanics feel like they dull or remove some of the most enjoyable loops of the game.
So do the thematic highs match the mechanical lows? If you’re a fan of Fall of Magic I’d say that City of Winter is worth exploring just to see what Deernicorn have done with the system, but the hefty price tag for the full game - canvas matt and all - is a bit of a pill to swallow for a game that I feel doesn’t hold together as good as the original. If you’re choosing between the two, I’d say go with Fall - it’s still my favourite and I think it’s the one I’ll continue to play more of, going forward.
I believe I first encountered Heart of the Deernicorn’s map-focussed storytelling game Fall of Magic at one of the many games on demand spots at Wellington’s KapCon. I can’t remember who was running it, but I do remember instantly being enchanted with the large map, the minimal narrative-first ruleset, and the general vibe of the whole thing.
Since then I’ve played Fall of Magic many times, both as a player and as a facilitator, as one-off sessions at conventions or as multi-session campaigns in the comfort of my own home. It’s rapidly become one of my favourite games. So when Deernicorn announced they were producing City as a spiritual successor to it, I knew I had to get it.
In comparison to Fall of Magic, City is bigger, with more rules, more maps, more cards, and I’d say more variety in terms of play style. I’m not convinced this gets us a better game, but it examines many of the same mechanical elements and themes from slightly different angles, and I have nothing wrong with that.
In City of Winter, each player takes the role of a member in a larger family. Over the course of the game, your family will flee your hometown and journey overland towards the titular City of Winter to try to escape the encroaching Umbra. At each location you will get a chance to show off the traditions you’ve brought with you, as well as being exposed to the traditions of the place you’ve just arrived at. As you travel on, you’ll need to decide whether you stick with your old traditions, or start to shed them in favour of the traditions you’ve picked up along the way.
During a round of play, each player gets a turn. On your turn, you get to pick one of the many scenes from your current location.
In each scene, you’ll pick either to share a tradition that you currently have, or witness a tradition from the location you’re currently at. If you share a tradition, you pick a card from your (pre-existing) hand of traditions, and hold it. If you witness, you get someone else at the table to draw a card from the relevant deck, and hold it. Then, during the scene, whoever is holding the card can play it to introduce that element into said scene. Once the scene is over, either you pass your tradition card to another player of your choosing (if you shared a tradition), or get to add it to your hand (if you witnessed).
That’s the basics of the game right there, although there’s some additional twists. You travel towards the City itself by, at any point, deciding to migrate - in which case you share a scene which shows why your character wants to up sticks, and then you sit out the rounds until everyone else has decided to move on as well. Once everyone has decided to migrate, you slim down your hand of traditions and move to the next location on the board, until eventually you reach the City.
In addition, you may always decide to advance time, closing the current chapter of your adventure. Every time you do this, everyone ages up by about 10 years, gaining a little bit more experience and some additional bonds with your family.
There’s some more stuff around the edges here - the City itself has a whole set of rules for travelling between districts, and the decks of tradition cards vary from location to location (although they’re not always completely different - sometimes you see traditions from your past pop back up like old friends, which is quite nice). But overall, that’s how this game plays.
If you haven’t played Fall of Magic before, you might think that the above barely sounds like enough to run a game. So I’ll let you know a little secret that you work out quickly upon playing either of these - the game lies only partly in the rules, with the other part embedded in the scenes appearing in each location. In Fall of Magic the folks at Deernicorn did a great job of controlling the narrative flow by ensuring each scene has a set of appropriate prompts - either cajoling more details out of each player, encouraging relationships between characters, or pushing towards resolution depending on the point in the game.
Compared to Fall, City generally has more mechanics. That’s how sequels tend to work. Overall, these mechanics reflect the change in the theme of the game: from a group of travellers touring the land, to a group of refugees fleeing a creeping disaster and starting a new life.
The most obvious change, straight off the bat, is the addition of tradition cards. In Fall of Magic each scene had its own prompt, that the director of the scene (it the player whose turn it was) would need to weave into the scene before its end. In contrast, City of Winter passes this responsibility to the tradition cards. Whether you’re witnessing or sharing a tradition, that card acts as the scene’s prompt. Only one player knows the contents of that card at the beginning of the scene, and it’s their responsibility to ensure it comes out in play.
Another set of smaller changes all combine to give a feeling of character - and party - growth and development. In Fall of Magic, characters are defined by relatively static traits.2 Throughout the game you have a few opportunities to change those traits, or other things about your character, but those opportunities are few and far between and when they come up they feel like exceptions - usually they come about through magic or other weird forces. In contrast, your character starts City of Winter with a number of traditions (things about your culture that resonate with you) and bonds to other characters - either player-controlled or side characters. Over the course of play you’ll get a chance to trade traditions with others (through participating in scenes) and add bonds (as your character ages), altering your character’s outlook, personality, and relationships with others. After a few sessions it’s often interesting to see who’s held onto their original tradition cards, and who’s swapped them out for exciting new traditions.
And finally, of course, this is a game that expressly allows for character death and supplies mechanisms for players to remember passed characters and take up the mantle of a new character, continuing the family. This game has no express end condition - unlike Fall of Magic, where you’ll eventually reach the land of Umbra and do whatever it is that you need to do. You could play this game forever, following the children, and grand-children, and great-grandchildren of those first refugees as they slowly forget the land they came from and their ancestors who journeyed here.
So what’s the impact of these mechanical changes? How does City stack up against Fall? My experience has been that where City of Winter builds on Fall of Magic‘s mechanics, it creates a more diverse experience with greater chance for character growth. But where it modifies Fall of Magic’s existing mechanics, it creates a less coherent experience than we see in the original game.
City of Winter is about refugees fleeing their homeland and building a new home in a new place. To that end, the new rules focus strongly on delivering that experience - of forcing you to choose between what you brought with you and what you find at your new home. The fact that your hand of traditions is limited - that at various points you’ll have to discard down to a set number - really forces you to decide whether you’ll take the new traditions of a place to heart (at the expense of the traditions you’ve brought with you) or to keep to the old ways, effectively rejecting those of your current environment. While other games cover this ground, the “passing time” mechanic lets us explore our characters’ reactions to new cultures not just in the first year of contact, but over a decade or more of exposure. It may be that characters who are initially closed to new cultures find themselves opening up over time, trading old traditions for new, or that those who are initially receptive to new traditions actually find themselves discarding them when forced to choose.
Honestly, the passing time mechanic is one that I think is almost undersold in the game. In our group I’ve seen our players use this mechanic as a chance to step back from actor stance and consider the family from a more netural point of view, allowing us to tell stories that would be difficult or impossible to tell in usual linear scene-by-scene play. We’ve house-ruled in montages once or twice to help flesh out the intervening years, and it always ends up taking us half a session as we talk through everything. Fruitful space for creativity indeed.
The one issue with this mechanic is that there’s not enough spaces on the map where I’d feel comfortable with our family passing time prior to reaching the City itself. The majority of the locations are so travel-focussed (hitching up with a trade caravan, for example, or boarding a ship) that spending several years at that location feels weird and counter-intuitive. I’d initially expected to have the first half of the game be our family caroming from temporary home to temporary home, our first characters spending decades of their lives displaced from any permanent home, some characters even being born on the journey, before finally arriving in the City and claiming some place we could stay for the foreseeable future. Instead we found ourselves migrating onwards as soon as we’d gone around the table once, not necessarily because of impatience, but because it felt true to the narrative.
Despite the flaws, though, those new mechanics give you a broader scoper for play - they generally feel like a net positive. On the other hand, the modifications to existing mechanics feel like they weaken the game. An example: in Fall of Magic, every scene is paired with a prompt. This means that moving to a new location is like Christmas morning, with everyone examining the scenes and their associated prompts and immediately imagining what they mean for their character. Importantly, it also means each scene and its prompt have been written to evoke a specific feeling and push for a certain type of scene in play. Is this helped by the fact that Fall of Magic is, despite the various branches in the path, a linear story with a predetermined narrative cadence? Absolutely.
What City of Winter gives us instead is a system where each scene prompt is either (if you share a tradition) selected from your hand, or (if you witness) pulled randomly from a deck. There’s a good reason for this - it enables the constant tension between holding onto your past or embracing new traditions which reinforces the theme and leads to character growth. But this means three things:
This isn’t the only modification to rules - but I think it’s by far the most drastic in terms of impact on play. Having played both games back-to-back I feel the play in Fall - specifically the action of picking scenes and then driving narrative in them - was much more fluid and natural specifically because every prompt was hand-written to go with the scene and everyone knew it ahead of time. It let me pick more appropriate and interesting scenes for my own character, and also set meaningful stakes and push towards meaningful conclusions when participating in others’ scenes. In contrast, I vividly remember reaching the titular City of Winter in City, getting settled, and then slowly gaining access to more and more of the city as our characters spent more time there. But even though narratively it was interesting to have new locations open up to us, the only change it made to play were a few new suggestions for scene setting - the prompts (that is, the traditions we could witness or share) largely stayed the same.
As mentioned in the caveat at the top, we’re most of the way through our campaign of City of Winter. We’ve enjoyed our run - the thrill of unrolling the map and seeing our next location, the back-and-forth of collaborative world-building, participating in each others’ scenes as our family’s bonds have developed over time. We’ve arrived at the City of Winter as a group who’s spent decades on the road, set up a new home for ourselves, and given the next generation as much of a leg up as we could. Members of the troupe have found themselves past their prime, having spent their best years on the road, never given the chance to settle down and make a name for themselves. In other words, it’s let us - a group of people who still live in the city they grew up in - tell our own little immigrant story.
But at the same time, it just feels like something is missing from this game. If we take as granted that rules matter, that we use mechanics to enhance the experience beyond just pass-the-stick into something better, we should expect our rules to drive towards the kind of play the designer intends. Clearly the rules in City are doing so - the fact that we’ve naturally fallen into telling immigrant stories with our characters shows that this is the case. But it feels like something has gotten lost in that shift.
City of Winter is still an evocative and interesting game, and I definitely want to play it again several times to see how I can approach the story differently, with different characters and different approaches to its new mechanics. But I can’t see it supplanting Fall of Magic any time soon.
]]>After several months of abortive fiddling with my page’s CSS in an attempt to make things look nicer, I think I’m finally getting somewhere. Because I never practice what I preach, all my cosmetic changes have been sitting on my main branch, so I’ve been prevented from publishing anything until the website looks nicer. We lie in the beds we make I guess.
The last six months have been characterised by a set of disappointing DNFs1, alongside a bunch of re-reading old favourites. At the time of writing - in the period between Christmas and New Year’s referred to by a friend or two of mine as Liminal Spacemass, I’ve been getting stuck into Robert Caro’s The Power Broker, although I’m nowhere near far enouigh through to add it to this list.
Even with rereads and DNFs, I’m pleased to say I have enough for five entries in my regular installment.
Translation State - Ann Leckie. Leckie is noted for writing the Imperial Radch trilogy, which got a bunch of nominations and awards. Since publishing these three books she’s also written another two set in the same universe - Provenance and this book, Translation State. I didn’t mind Provenance but it didn’t quite have the hit of the Imperial Radch books. I’m not sure why - was it a lack of scope or ambition, perhaps? I might need to reread it to get a better handle. Either way, Translation State doesn’t lack that scale that I think I was maybe missing.
This is a story told from a number of different points of view, and also explores the culture and lives of the myserious Presger, strange aliens whose inhumanity is a core driver for some of the events of the original trilogy. While the story itself is captivating, I feel the greatest achievement of the book is managing to shed light of the motivations of the Presger and their actions in the original trilogy.
The Good Enough Job - Simone Stolzoff. Is this the only non-fiction book on this list? I think it is.
This is a book about workism - that always-on, job-as-identity mindset which pervades capitalism and especially white-collar work. It’s a nice combo of “how did we get here” and “what can we do about it”. And, really, there’s always something cathartic about being preached to when you’re part of the choir.
Tehanu - Ursula Le Guin. The Earthsea series (quintet?) is a staple of post-Tolkein fantasy and fantasy in general, but it’s also a great showcase of Le Guin’s career, spanning as it does around three decades of her life. Tehanu is a definite turning point, as the focus of the series shifts from adventure and discovery to introspection, contemplation, and self-discovery.
Le Guin never leaves behind the fact that Earthsea is a fantasy world, but she also clearly demonstrates how fantasy doesn’t have to be world-altering, nor do the stakes have to be apocalyptic in scale to be clearly meaningful to the book’s protagonists. The first three books in this series are about a wizard of great power sailing to the ends of the earth to prevent magic draining out of reality. This book is about an old woman and her daughter dealing with death and growing up and growing old. In some places it feels distinctly, deliberately - almost radically? - mundane, but in some places it drips with magic, perhaps all the more frightning for those who witness it if only because of the contrast between these two poles.
Babel - R. F. Kuang. I’ve worked out over the past few years that I love a Bildungsroman, even more so if it’s in the mold of “child goes to magic school”. Well, Babel has that in spades.
The book follows a group of gifted kids from the edges of colonial Britain during the Victorian era as they attend Oxford University’s Royal Institute of Translation, learning how to harness the magic of meanings shed when words are translated from one language to another. Even if the book stopped there it’d be checking a number of boxes for me. But that gets us about halfway through - in fact, it’s basically a set up for the second half, where we take flight into a roller coaster ride through the excesses of colonialism, capitalism, and the entrenched racism and classism of British society.
This is an excellent book, one of the best books I read all year. I want to re-read it at some point, but it’s an intense ride. Perhaps in a year or so.
The Magician’s Land - Lev Grossman. I’ve read Grossman’s first novel in this trilogy about four times now. See above about how much I love a Bildungsroman about a kid going to magical school. The last few times I re-read it I remember not particularly enjoying the following books of the series - I think it’s something about how when - if - you plan on writing beyond everyone graduating2, you need to pivot at some point to whatever story this is about once everyone is ejected into the crucible of real life, and at the last time of reading, I’m not sure I was ready for that pivot.
Perhaps this time I was: the two following books felt much stronger than they’d ever done before.
ie “Did Not Finish”. Life is too short to finish reading books you don’t enjoy. ↩
And everyone will graduate. I suspect that any book or series like this which keeps its characters in a limbo of school attendance for too long will quickly become stale, and also that the novelty and half of the drama - especially for this series - is in what happens after. ↩
I’ve actually been working on this over the last couple of months, after reading through a bunch of interesting posts on digital gardens and thinking through how they overlap with my thoughts on the purpose of this site. I’ve written a lot of stuff over the past ten years1 which I’d consider to be relatively timeless - not necessarily in that it was earth-shattering, but more in that its value hasn’t decreased over time. That made me think about adding some kind of digital garden section to the site, although that made me start wondering how things like my projects and writing subsections intersected with a digital garden. And once you go down this path, well, you might as well refresh the CSS at the same time, right?
I’m publishing this now, not because I think everything is finished, but more because I need to hit “publish” on these changes at some point or be sunk into a hole of perfectionism for the next year. Having a hobby like maintaining a home-cooked website is tricky to keep up when you have a tiny two-year-old being demanding your attention most hours of the day - it’s the kind of project which progresses slowly, in fits and starts. So having something “good enough” should be enough of a trigger to push to the public.
Hopefully I’ll get to spend the next few months filing off the rough edges, adding features where they need to happen, and the like. In the meantime, I’ve written up a bit about my choices…you guessed it…in the garden.
It’s a bit bare right now. More to come. I hope you enjoy the chance to take a wander once in a while.
Wow, I’ve never measured it before, but I guess this site went through its ten-year annivesary in April last year. ↩
In a nutshell, Matrix is a messaging service, just like Signal or Facebook Messenger or MSN Messenger or Google Talk or what-have-you. It’s got some cool features which really draw me to it, but it can be a bit confusing to dive right in. So this post covers two bases:
If you’re reading this and you’re friends with me on Facebook - or if you’ve left Facebook and are looking for a way to keep in contact - maybe you want to dip your toes in the water. Drop me an email and I’ll send you my username so we can switch our primary comms channel!
The social media ecosystem is a cartel of monocultures. The vast majority of popular one-to-one and small-group messaging services are a subset of that, and suffer exactly the same problems. Depending on where you are in the world, and your demographic, you’re probably familiar with at least one of these. For me, an older milennial living in New Zealand, our monolith is Facebook, but what I say about Facebook will apply to every other service of this type.
We know, I believe, that these companies and their business models are bad. We even know, deep down, that we’re not the real customers here - we’re just the product, willing to sell our attention and data in place of money, because we all love a free lunch. Once you’re signed up, the inertia of the network effect keeps you there, unless the owner completely screws up.
If you agree with the above, I think you’re in a similar place to me: you’re either putting up with your current service now because switching would be a hassle, or you’re vaguely unsatisfied and have been searching for the right alternative. You might have found services like Slack, Discord, or Signal to fulfil your needs: while I feel like these are all miles above the current incumbents, I can’t help feeling like we’re trading one walled garden for another.
Obviously, based on the premise of this article, Matrix has grabbed me in a way that these other alternatives haven’t. There’s lots of good things about it - I love how well it handles both ad-hoc conversations and persistent rooms, it has a bunch of nice quality-of-life features that we’ve kind of gotten used to in other clients, and its main client, Element, is pretty snappy. But the thing that sets it apart from pretty much all the other competitors is that it’s not just a service - it’s also a protocol, and an open one at that.
What does that actually mean? It means that anyone can run a Matrix server1, and they all talk to one another. In practice, it means that it doesn’t matter whether I have an account at matrix.org or mtrx.nz or some other Matrix homeserver - I can still message you and chat wherever you happen to be. There’s no single point of failure in the network and no one server dictating what happens. Now in practice the foundation who maintains the protocol also hosts the largest server and publishes the most commonly-used and feature-complete client, but that’s how these things often go.
Matrix is actually part of a whole host of apps which have sprung up to take advantage of (or rapidly adopted) the open ActivityPub protocol, which lets servers and even applications talk to each other through a kind of “universal translator” of activities. Mastodon is one of the more well-known apps on “the fediverse”, as this community of tools is known. For every social media website that exists right now, someone has probably built (or is probably building) an equivalent on the fediverse, although given most of this is done not-for-profit and/or on a shoestring, the interface may not be as slick as the more traditional/centralised counterpart.
When I’m feeling optimistic, I hope that the end result of the current backlash against social media platforms (Twitter, Facebook, Reddit…) is a shift away from centralisation and commercialisation, towards federation and a smaller, cozier, less expoitative web. Regardless, if you’re going to spend the effort to up sticks, to shift to a completely new service for any of this, I figure why not go for the one which offers you something a bit more philosophically and ethically thorough than the current profit-driven model. If you’re going to die on a hill, might as well make it a hill you agree with.
So let’s say you’ve read this far, and you’re curious. You want to explore an alternative to Facebook for your social messaging needs, but you’ve been waiting for someone else to make the first move. How can you join me over there? I’m so glad you asked.
Setting up Matrix is a little bit more complex than joining most messaging services, but honestly, it’s fine. Here’s how you go about it:
1. Pick a server. As I mentioned before, Matrix is like email - just like how one person can be on GMail, someone else can have their old hotmail account from twenty years ago, and a third person can have an email address sitting on their own domain, you can pick one of a number of Matrix servers to be your “home server”. Here’s a big ol’ list of home servers including some high-level details on how they’re run.
In reality, you can just jump on the main server at matrix.org and be fine. If you’re New Zealand-based, you may want to join me on mtrx.nz, a service hosted by these fine folks.
Again, though - it doesn’t matter too much! Just like how email works between servers, you will be able to talk to anyone on Matrix regardless of your home server.
2. Create an account. Whichever server you pick, make an account there. Link it to your email and all that jazz.
3. Grab a client. Matrix’s decentralised nature means there’s a few clients out there for you to play around with. Most home servers host their own web-based client, but you may also want to download one for your computer and/or phone. I’ve found Element to be very good - it’s made by the people who make the Matrix protocol, and it’s pretty fully-featured. It’s also supported on most platforms.
And…you’re on! Now all you need to do is find some friends to talk to. If you’re a friend of mine (and not just some random person visiting from the internet, hello random person from the internet!), drop me an email or message me on your non-Matrix service of choice and let me know - we can exchange details and you’ll have a friend on there. Congratulations on starting the journey away from Facebook’s monopoly!
Yup, this is how they get you. The Catch-22 of network effect is that no one wants to shift off of the dominant platform because all their friends are there, and all the folks you know are on the dominant platform because no one has shifted off yet.
It’s easy to think we don’t have a choice in this matter. We do, but the cost is high enough that the easy choice is to stay with the company/platform we know is bad, because we want to talk to our friends. It’s a choice that social media companies rely on to keep customers beyond the point where their product stops being a media darling.
I don’t mean to tell you that your choices are bad. Many people don’t have the time to work out how to change messaging programs, or rely too heavily on their existing (and heavily embedded) networks within these systems. I still have Facebook Messenger installed on my phone, and I’m not likely to uninstall it any time soon.
If you’re at the point where you’d like to move platforms, but don’t want to be the first one to move, let me offer you the chance to be the second one to move. If you’re on Matrix, and I’m on Matrix, maybe we can persuade a mutual friend to join us. This is how we start to shift.
Of course, in practice this means that a few folks run Matrix servers, and we just pick the one that we want from that limited list. But this is still, in my opinion, miles better than the alternative where the person defining the protocol also hosts the only server and builds the only client, locking us into the environment they’ve decided on. ↩
(“Hey Jan”, you might be saying to your computer screen, “wasn’t the Eurovision Song Contest like months ago? Hasn’t all the heat died down?” To which I’d tell you: yes, but I have a kid and I took this as an opportunity to re-learn D3, which all took time, and then I got distracted a bit half-way through, and then I returned to it. And while it might not be as hot-button as it was at the time I started writing it, I’m still pretty proud of some of the data viz here, and I think it’s still worth showing off. Also, you should probably stop talking to your computer screen, it’s unhealthy.)
If you live in New Zealand, you have two choices when it comes to your awareness of the Eurovision Song Contest:
Our household currently falls into category two. For those who did not watch, here’s the run-down on the Eurovision Song Contest 2023 that you need to know to understand this post:
As a result of this there’s been a lot of discourse about the role of the jury in voting, the inherent bias of jury votes towards established music professionals versus newcomers, the need for a jury vote when televoting is so reliable and popular, and so forth. I don’t have anything to add to that. But in this I saw a chance to make some pretty graphs, and also to relearn D3. So in doing that, I tried to make some visualisations to explore:
Data is from Eurovision World.com.
The current Eurovision voting model - where the jury and audience both get to give points to entries - only came in from 2016 onwards. Before that, countries would usually have both a jury and their audience participating in voting, but the votes would be combined and the country would give out one set of points. For this reason, data only exists from 2016 onwards. There was on Eurovision Song Contest in 2020 - it was cancelled due to COVID-19.
From year to year, differing numbers of countries will participate in the Eurovision, and in 2023, the rest of the world was allowed to vote as one big block, providing another 12 points on the televote side. Because point totals differ from year to year, when we compare entries across years we’ll measure points by “percentage of total” rather than raw point values. For example, if an entry gets 325 audience points, and there’s a total of 1,450 audience points total given out that year, the even will be shown as getting (325 / 1,450 = ) 22% of audience points.
Here we can see the spread of votes for 2023, split into jury and televote portions. Sweden and Finland are way out to the right and top respectively, clearly leading the jury and televoting respectively. Third- and fourth-place Israel and Italy are surprisingly close to the midline, with very small discrepencies between their jury and televote point totals. And then there’s the rest of the pack, where skews are a bit more pronounced: Norway, Ukraine, and Croatia hug the y-axis, crowd favourites even if they didn’t garner the jury’s attention, while Estonia and Australia get the opposite treatment.
So we can see there is a voting split - we can definitely see jury and audience favourites. But is that just the natural split we’d expect to see when different people vote on things? Or is this year an outlier? To find that out, we need to look at the points allocations from previous years.
Because that’d be a lot of data points, in the plot below we just look at the top three each year, from 2016 through to this year:
Immediately we see that Tattoo got a lot of the jury vote - 16%, to be exact. This was equalled by 2017’s winner, Amar Pelos Dois, but those two are real outliers. In comparison, while Cha Cha Cha was definitely popular with the audience it wasn’t the most popular song in the 2016-23 period - last year’s winner Stefania managed to grab 19% (!) of the televote (compared to Cha Cha Cha‘s 17%). While these two are the songs most popular with the viewing public, others are hot on their heels, with a number of songs receiving 14% or more of the televote.
So there’s always been jury favourites and audience favourites. But who’s more likely to win? And have we seen a deepening of this trend over time?
To measure this, let’s look at the jury bias of the first-, second- and third-place songs. We define the jury bias of a given song as the proportion of the jury vote the song received (as a percentage) minus the proportion of the televote the song received. So for example, Tattoo received 16% of the jury vote and 11% of the televote, so its jury bias is 5%. The average (mean) jury bias for each placement is shown as the hollow circle in each row.
This starts to tell us something more interesting than just “the audience’s favourite song didn’t win this year”: specifically, it tells us that the audience’s favourite songs (or at least, songs which are favoured by the audience more than the jury) tend to win. The only other first place song which scored better with the jury than the audience was 2017’s Amar Pelos Dois, and even then the difference is so small as to be basically even.
The mean jury bias for first-place songs is -2.9 percentage points, meaning that on average the top-placing song scores around 3 percentage points more with the televote than the jury. This pattern sticks around for the top six spots, until finally, from spots seven through ten, we see that the mean jury bias hovers around zero.
(Why does is pay to be a televote favourite? I haven’t done any analysis of this, because this post is already well overdue, but a quick check of the numbers suggests that jury votes tend to be spread across more songs, while televotes tend to cluster around a few favourites. That means even if you are a jury favourite, it’s difficult to get that critical mass of votes to carry you across the line. Meanwhile, if you’re an audience favourite you’re likely to grab your douze points from a few countries’ televotes, which means more points total.)
So it looks like the voting split was pretty drastic this year - and while we’ve seen larger splits in the past, we’ve never seen this kind of split - a marked jury favourite winning top vote - in the years where we’ve had this kind of granular televote/jury voting data. This bucks the trend - usually we’d expect to see a televote favourite (or something with combined jury and televote appeal) grabbing top spot, and if there’s a jury favourite it’ll come in at second or third place.
If you’re feeling bad for Käärijä getting second place, you’re justified: based on previous trends, his act was a shoe-in to win. But if you feel like jury voting is ruining Eurovision, you can rest easy knowing that what we saw this year appears to be an outlier.
]]>I’m back with a mid-year review of some books I read and enjoyed! Once again, in the interest of brevity and as an excuse to publish actual content to this blog, I’ve decided to run this year on a six-monthly shift.
The last six months I feel like I’ve really got to read some good books, perhaps inspired by words of wisdom from Adam Sternbergh. In particular, I set myself the “challenge”1 of reading through all of Ursula Le Guin’s Hainish Cycle, the mainstay of her science fiction work. I really enjoyed the Earthsea series when I read it however many years back2, and I read The Dispossessed and The Left Hand of Darkness at various points, but the whole backdrop of those books always felt like there was another movie going on just out of frame, involving the interstellar politics of the Ekumen. At the time of writing I’m still forging through these books, but the words which readily come to mind here - “challenge”, “forge” - are really counter to the effortless feel of immersing yourself in a decades-long conversation about society and humanity.
With so many books to choose from, I’m going to counteract my last entry and give you six books I enjoyed over the past six months.
Devil House - John Darnielle. A true crime writer settles in to a little out-of-the-way town in central California to research a murder from decades ago that the town would honestly rather move on from. Through the course of the book we see the author uncovering the story he’s going to put to paper, while also wrestling with how his work impacts the real people who still live in these communities.
I read Darnielle’s Wolf in White Van many years ago and greatly enjoyed not just the general vibe of the book, but also the roleplaying-adjacent topic. Devil House has the same things going for it, and I enjoyed it for the same reasons. I think maybe the story has a bit more meat on it than Wolf in White Van, but I think I’ll have to sit with Devil House a bit, and perhaps have a re-read, before passing judgement on the books’ merits relative to each other.
I also read Universal Harvester alongside this, and while the vibes are great, the plot doesn’t feel like it holds together quite as well as the other two.
The Most Important Job in the World - Gina Rushton. The tsundoku next to my bed is higher than ever, and this book was in there, if only briefly. I bought it in physical form after a short review on Dense Discovery, as it felt appropriate given the kid and my weird relationship to family and parenthood. I thought it was going to focus on the history of gender and parenting, but instead got treated to a searing, soul-enamel-scouring3 introspection by the author on what it means to be a parent in a world of gender and racial inequality and climate change.
This is a hard book to read as a prospective or current parent, but the message is - I think? - hopeful. I feel I came out of this book changed, and that’s what art’s all about right?
Parable of the Sower - Octava Butler. A post-apocalyptic book about a black teenager with a vision of a new religion in a decaying America. This kept on coming up on folks’ recommended lists, so I finally got around to reading it. It’s wild to think that this was published in the early nineties: it feels incredibly modern not just in its depiction of a near-future conservative America in a state of capitalism-induced collapse, but in what the authorial camera focusses on. It also reminds me of Avery Alder’s Dream Askew: “Imagine that the collapse of civilization didn’t happen everywhere at the same time. Instead, it’s happening in waves. Every day, more people fall out of the society intact.”
Despite this - despite the grand vision, the detailed world-building, etc. - something about the book didn’t quite gel with me. I still enjoyed it and found it very engaging, but perhaps I’ve had my fill of precocious young protagonists.
The Yiddish Policeman’s Union - Michael Chabon. An alternate-history Jewish-diaspora film noir murder mystery. There’s a lot of words in that last sentence and it doesn’t even get into the actual plot of the book, except that it’s exactly what you’d expect.
This was another book I saw on a list and decided to read on a whim. I wasn’t quite prepared for it, but I felt it worked wonderfully. In saying that, I feel like it’s the kind of book where a bunch of content and perhaps subtext went right over my head. Perhaps that just means I need to re-read it in a year.
Four Ways to Forgivenness - Ursula Le Guin. I had to pick one book from my recent reading project, didn’t I? Four Ways to Forgivenness (later published as Five Ways… with an additional novella on the end) is a book about a twin planetary system that’s dealing with its slave-owning past and present. It’s written as a series of short stories and novellas, all of which interlink gently and none of which really hold your hand too much regarding the surrounding context of events. That means you naturally start off a bit confused and spend the first story working out who’s who and what it all means (or I did, anyway).
By telling the story across multiple points of view and points in time, the book is able to talk about a world’s changing relationship to race and gender in a really in-depth way. I normally prefer novels to short stories - partly because the length of a novel allows you to weave a bit more of a complex story with a bit more depth and time to it, but the binding common world, and the recurrance of characters and situations between these stories, lets this book do that across multiple stories. It really makes this something worth coming back to.
Quiet - Susan Cain. Or, to give this book its somewhat wordy full title: Quiet: The power of introverts in a world that can’t stop talking. This is a book about introversion: why it happens, what it means, why it can suck, why it’s great. The book is unapologetically in the corner of introverts, with the author being a self-acknowledged introvert who has had to “perform” the extrovert in previous jobs.
As a pretty obvious introvert who’s grown good at wearing the extrovert mask over the past decade or two, this book resonated pretty strongly with me. If that also describes you, you may enjoy this book just for that, even if you don’t learn anything new from it.
Challenge is a strong word I think here, but you get what I mean. ↩
I first read A Wizard of Earthsea as a teenager - my parents gave it to me as a birthday or Christmas present. And I hated it! I don’t know whether I refused to engage in its core conversation about death, or whether the whole thing just went straight over my head. Whatever the case, I remember bouncing off of it hard. It took me a decade to go back and find out not only that it was a great book, but that there were more in the series. ↩
You know that feeling when you’ve just read or watched or listened to something that danced a bit too close to the eternal truth that everything is finite and no one knows what you’re doing for your own comfort? With me it gives me that feeling you also get when you eat too much rhubarb and your teeth feel like they’ve had the very top-most layer of their enamel gently removed - you end up feeling a little raw and inclined to start answering innocent questions like “how are you?” truthfully. That’s what it means to scour the enamel of your soul. ↩
Like many GMless games that emulate the traditional GMed roleplaying game framework, Society doesn’t as much eliminate the roll of GM as it does spread it out amongst the group. Specifically, the role of GM as scene-framer is instilled into the role of the “instructor”, which rotates between players. This is great, as almost all of the rules in the game provide the instructor with the relevant structure and prompts to do their job of framing their scene, working out who’s there, etc. In other words, the instructor’s job is less about coming up with the next scene whole cloth, and more about taking the constraints, prompts, and so on provided by the game, and working out what the next scene looks like.
This has been all fine for the majority of our scenes, but in our last session1 I came to the point, as the instructor, that I really wanted to land a good scene given where we were in the story. I didn’t want to just throw some spaghetti at the wall and see what stuck: I wanted to spend some time ensuring that my pot was 100% sticky spaghetti.
(That’s how spaghetti works, right?)
At the same time I’ve recently been listening to the Friends at the Table podcast, whose most recent game in their Bluff City series was Avery Alder’s Dream Askew2. One thing that stuck with me, listening to the game being played, was its idea of idle dreaming. From the manual:
As the map is being sketched and the community is being fleshed out, you enter into a mode of play called Idle Dreaming. This is a time for questions and curiosity, for tangents and musings. Talk about whatever is interesting, or unknown, or scary, or beautiful about this place that you’re building together. Make up details about the landscape, its history, and its residents. Setup becomes play, one flowing directly into the next.
…
Idle dreaming stokes curiosity and excitement, and that leads into scenes. If ever a scene concludes and there’s uncertainty about what might happen next, it’s always fine to return to idle dreaming until a compelling answer rears its head and demands attention. With that said, it’s common that once the first scene emerges, the session quickly builds momentum and never returns to that starting place of idle dreaming.
- Dream Askew/Dream Apart, pp 24-25
I had a quick search through the rulebook to find this definition, and honest I’m surprised at how little attention is drawn to this technique. Don’t get me wrong, I think Dream Askew/Dream Apart do plenty of cool and novel stuff with GMless and diceless roleplaying which I’ve had lots of fun hacking into my own stuff over the years. But I think idle dreaming feels like the game’s sleeper hit.
Deceptively simply. The two paragraphs above describe it pretty succinctly:
It’s not ground-breaking because of its complexity or mechanical depth. The thing that makes this magic - at least for me - is that it gives me a framework to break out of a common fallacy in gaming: that the GM (or whoever has the GM hat on right now) needs to have all the answers, or needs to come up with them all on their own.
The other wonderful thing about this is that you don’t even need to tell anyone at the table that you’re using the technique. I didn’t say to the other players at the table, “OK, I’m going to do a little thing called Idle Dreaming, this is how it goes.” I just started asking questions, and led the conversation until I reached the, uh, the sticky spaghetti, to continue the metaphor.
Here’s the thing: I have vivid memories of running old, pre-release Dream Askew and finding that process between world-building and scene setting to be excrutiating, especially with newer players. The reason is simple: no one knows where to begin.
Why was this process so difficult? Partly because while the bones of idle dreaming existed within that copy of the book, they weren’t fleshed out at their own technique. And partly because without this process I just didn’t have a framework to guide me, other than saying to everyone, “So who thinks their situation is interesting enough to frame a scene around?”, and then listening to crickets.
The mechanic gives you authority to say to the table: “I don’t know what our next scene is, who wants to help me work it out?” And it frames it in a way to get people talking, about what they’re interested in, what they want to see, to try to ensure everyone has a stake in the next scene that gets played. Like all good narrative mechanics, it’s light-touch enough to get in, cue up the next action, and get out to leave you all just having a conversation.
And to loop back to the initial example of how I integrated this into our last session of Society: until I thought about applying idle dreaming, I had a few half-baked ideas. After around ten minutes of idle dreaming with the rest of the group, we had something compelling, that involved a number of different threads, and ultimately became the climactic scene of our campaign. It didn’t feel like something I authored solely by myself: it was something that we built together, that we were fully invested in.
That’s somewhere I wouldn’t have gotten on my own.
Both as in the most recent session we ran, and also as in the final session of the campaign. ↩
Dream Askew is published alongside another game, Dream Apart, both using the same mechanics. I’ll be referring to both games together, and their combined mechanics, as Dream Askew/Dream Apart for the rest of this post. ↩
It feels like over the past six months OpenAI’s various products - particularly ChatGPT - have gotten a bunch of press. ChatGPT is a large language model, which (as far as I understand) basically means you feed it a whole honking bunch of text, and it extracts information from that text and is able to then respond to questions by putting words together into something coherent. Basically, it’s faking being a functional human being, but then this is 2023, give it a break, that’s all of us.
You can go read all about its predicted impact on writing, art, school exams, creativity, and every other sphere if you want, I kind of feel 10% of the web now is articles like that. I don’t particularly feel like consolidating a paragraph of media responses to the technology, though - I want to write about things that interest me.
Like roleplaying games. Given ChatGPT can take basically any prompt we give it, and spit back something that sounds vaguely coherent, how can we use it to make roleplaying games better? After all, most roleplaying games are basically a bunch of words, right?
So in this post, I’m going to explore some common potential applications for ChatGPT when it comes to roleplaying games, both tabletop and live action. Hopefully these give you an idea of where it excels, where it falls flat, and where you could use it yourself.
It seems like ChatGPT is:
And when we consider how ChatGPT is faking being a human being, it makes sense that we get that kind of tier list out of it.
Most responses were collected from ChatGPT Jan 30 version, and some from the Feb 13 version, using the company’s free research preview. I didn’t try to regenerate any responses, instead opting to refine what I had through follow-up questions. When I did that below, I’ll let you know.
This is a really common thing I find myself floundering with when I write LARPs - the first five characters I’m fine with writing up, and then after that my brain gets increasingly fried and my prose increasingly sparse. Added to this, I’m a serial sufferer of “more characters than plot” syndrome - I know that this game should have around 20 players, but for the life of my I can’t work out how characters 16 through 20 fit into that plot.
Thankfully, ChatGPT has my back1:
Write a three paragraph character sheet for a supporting character in a live action roleplaying game. The game is about a group of friends at a magical high school in England who have snuck away for a weekend of relaxation before their year-end exams. The characters should explore themes of coming of age, friendship, and rivalry.
Name: Liam Johnson
Age: 17
Appearance: Liam is a tall and lean young man with messy, curly brown hair and piercing green eyes. He has a charming smile and a confident demeanor. He’s always dressed in the latest fashion and is never caught without a stylish accessory or two.
Personality: Liam is confident, charming, and popular. He’s the life of the party and always knows how to make those around him feel comfortable. He’s also fiercely competitive and will stop at nothing to be the best in everything he does, including academics, sports, and socializing. He sees his rivalries as friendly challenges, but his competitive nature sometimes causes friction with his friends.
Backstory: Liam comes from a wealthy family and has always been given everything he wants. He’s grown up surrounded by the best of everything, from the finest education to the latest technology. However, despite his privileged upbringing, Liam is not content with just coasting through life. He wants to prove that he’s the best and will do whatever it takes to make sure everyone knows it. This drive for success has led him to become one of the top students at the magical high school and a star on the Quidditch team.
So what do we have here? A very passable outline of a character whom we could flesh out into something more coherent, adding in our own plot hooks, relationships, and the like. I mean, don’t get me wrong, as it stands it reads like a slightly-too-Marty Stu love interest in a Harry Potter fan fiction (the Quidditch bit at the end just helps remind you that these are all cobbled together from The Internet), but it’s still not bad!
One of the criticisms levelled at ChatGPT has been that since it just regurgitates information from its corpus, and its corpus is online text at large, it tends to reinforce bias and stereotype in society. And I thnk Liam here is a perfect example. Of course, one of the nice things we can do is refine things, so I’m sure you could ask ChatGPT to make Liam a bit less square.
This was actually my first attempt to do something with ChatGPT. I showed it to a friend, who was suitably impressed, but metioned that they usually like having more links in their characters. That’s totally valid, so let’s try something a bit more connected…
One character alone is boring. Let’s see what happens when we get ChatGPT to build a faction with relationships.
Could you please generate a faction of five characters for a Live Action Roleplaying Game? This game is a soft science fiction whose theme should loosely mirror Firefly or The Expanse. The faction is a group of representatives from nomadic traders whose culture is reminiscent of Polynesian explorers. Each character should have a paragraph or two of description, including their personality, goals, and links to the other characters in the faction.
Certainly! Here are five characters for your live action role-playing game:
Captain Kana Laula - Captain Kana is the charismatic and confident leader of the nomadic traders. With a long history of successful trading voyages, Kana has earned the respect and loyalty of her crew. Her quick thinking and strategic mind often get her and her crew out of dangerous situations. Kana has a strong sense of family and community, and her ultimate goal is to ensure the prosperity and success of her people. She has a close relationship with the faction’s engineer, Keani.
First Mate Tama Makani - Tama is Kana’s second-in-command and right-hand man. He is a skilled fighter and navigator, with a no-nonsense attitude and a loyalty to Kana that borders on fanatical. Tama has a personal vendetta against a rival trader named Kalima, who he believes has wronged Kana in the past.
Engineer Keani Nalu - Keani is the mechanical genius of the crew. Her quick thinking and innovative solutions often save the day when the ship is in danger. Keani is a strong, independent woman who is respected by her crewmates for her technical expertise. She has a close relationship with Captain Kana, who she sees as a mentor and role model.
Medic Lopaka Hoe - Lopaka is the ship’s medic, responsible for the health and wellbeing of the crew. With a gentle and nurturing personality, Lopaka is beloved by everyone on board. He has a deep connection to his Polynesian heritage and often incorporates traditional healing practices into his work. Lopaka is also the ship’s cook and is known for his delicious meals that bring the crew together.
Smuggler Pono Kaulua - Pono is the wild card of the crew. As a successful smuggler, he has a network of contacts and information that can be valuable to the traders. However, his unorthodox methods and tendency to bend the rules often put him at odds with the rest of the crew, especially Tama. Despite this, Kana trusts Pono’s instincts and allows him to operate independently. Pono has a strong sense of loyalty to the crew and will do anything to protect them.
Now we’re talking! The bot has done remarkably well to keep some internal consistency here - for example, Kana’s and Keani’s descriptions agree well on the relationship between them. The main issue I have with the faction is that everyone is very chummy with everyone else - ideally there should be a bit of bite in these relationships, to keep things spicy in play. Thankfully, this doesn’t have to be our final draft.
In addition, I like how the bot mirrors your tone. When I just ask it straight up for something, it comes back with just the goods. Add in some pleases and it seems to perk up and provide some personality.
ChatGPT lets you refine your answers by asking the bot to modify things. Here’s an example, with the big changes bolded.
How could I alter these relationships to add a bit more conflict into the faction?
Here’s a revised version of the relationships between the characters, with added conflict:
Captain Kana Laula - Captain Kana is the charismatic and confident leader of the nomadic traders. With a long history of successful trading voyages, Kana has earned the respect and loyalty of her crew. However, her quick thinking and strategic mind often put her at odds with the faction’s engineer, Keani, who has a different approach to problem-solving. Kana has a strong sense of family and community, and her ultimate goal is to ensure the prosperity and success of her people, even if it means making difficult decisions that not everyone on the crew agrees with.
First Mate Tama Makani - Tama is Kana’s second-in-command and right-hand man. He is a skilled fighter and navigator, with a no-nonsense attitude and a loyalty to Kana that borders on fanatical. However, his vendetta against rival trader Kalima often puts him at odds with Captain Kana, who believes in finding peaceful solutions to conflicts. Tama’s hot-headedness and tendency to act before thinking can also put the crew in danger.
Engineer Keani Nalu - Keani is the mechanical genius of the crew. Her quick thinking and innovative solutions often save the day when the ship is in danger. However, her independent streak and tendency to challenge Captain Kana’s authority sometimes creates friction between the two. Keani is a strong, independent woman who is respected by her crewmates for her technical expertise, but her lack of trust in authority can make it difficult for her to work effectively with others.
Medic Lopaka Hoe - Lopaka is the ship’s medic, responsible for the health and wellbeing of the crew. With a gentle and nurturing personality, Lopaka is beloved by everyone on board. However, his deep connection to his Polynesian heritage and traditional healing practices often puts him at odds with the faction’s smuggler, Pono, who sees them as outdated and superstitious. Lopaka is also the ship’s cook and is known for his delicious meals that bring the crew together, but his refusal to incorporate new and unfamiliar ingredients into his cooking can cause conflict with some members of the crew who crave variety.
Smuggler Pono Kaulua - Pono is the wild card of the crew. As a successful smuggler, he has a network of contacts and information that can be valuable to the traders. However, his unorthodox methods and tendency to bend the rules often put him at odds with the rest of the crew, especially Tama, who sees him as a liability. Despite this, Kana trusts Pono’s instincts and allows him to operate independently, but Pono’s loyalty is not always clear and he may put the crew in danger to serve his own interests.
A relatively simple request to alter the descriptions has given these characters a bunch more depth2. The whole crew still feels like a coherent unit, and you can still see the ties that bind them, but you can also see how these refinements start to add the hard edges of personality and minor conflict to the faction.
And the great thing is that we can keep doing this. I’m not going to add everything because this post is already pretty long and I stil have some more examples to give, but some other things I successfully asked ChatGPT to do with this faction included:
The above exercise got me thinking about how well ChatGPT could work in creating cultures and species for fantasy (or science-fiction) games. You can only stand so many fantasy games that are Tolkein (or D&D) with the serial numbers files off before you want to start creating your own analogues to elves, dwarves, halflings, and orcs. And you can only do so much thinking about world-building before you realise that mapping race (or, as we would call it, species) to culture monolithically is a bit reductive.
So, let’s see what happens when we give it the remit to create a fantasy species and three cultures present in that species:
Could you please generate a fantasy race? It shouldn’t mimic the tropes we see in Tolkein’s works or in Dungeons & Dragons (no elves, dwarves, or orcs). The description of this race should include physical description, variation within the race. In addition, could you generate three cultures that exist within the race? Each culture should have a few traditions, a distinct linguistic feel, and some basic relationships with the other two cultures.
Sure! Here’s a description of a new fantasy race, along with three distinct cultures within that race.
Race: Aeloria
Physical Description: Aelorians are a tall, slender race with elongated limbs and fingers. They have large, almond-shaped eyes that come in a variety of bright, iridescent colors. Their skin is thin and delicate, ranging from pale to deep blue, and is covered in fine, shimmering hairs that change color based on their mood and environment. Aelorians are known for their agility and grace, and are able to run and jump with incredible speed and precision.
Variation Within the Race: Although Aelorians all share similar physical traits, there is a great deal of variation within the race in terms of their abilities and powers. Some Aelorians are born with the ability to control the elements, while others can communicate telepathically with one another. There are also Aelorians who have the ability to see into the future, while others can manipulate time itself.
Culture 1: The Wanderers
The Wanderers are a nomadic culture that travels across the land, following the seasons and the migration patterns of the creatures they hunt. They value freedom and independence above all else, and reject the idea of settling in one place for too long. They are skilled hunters and trackers, and are known for their prowess in the wild. They have their own distinct dialect, filled with sounds and inflections borrowed from the animals they live among.
Traditions:
- The Wanderers hold an annual hunting festival, where they gather to share stories and compare their skills.
- When a Wanderer reaches adulthood, they must undertake a rite of passage that involves surviving alone in the wild for a full cycle of the moon.
- Wanderers communicate telepathically with one another and share a deep connection with the animals they hunt.
The answer went further to provide the other three cultures, as well as the relationships between them. I’m more impressed with this than I was with Liam in our first goal, but much less than with our faction of spacefarers above. Sure, the species isn’t a carbon copy of anything in Tolkein, but it still feels…well…elfy. The variation stuff seems to be trying to one-up itself as it goes, and the culture is a little insipid as well, I think.
I mean, I don’t want to take away from the fact that this AI generated the whole thing from a relatively small prompt in next to no time. That’s still mind-blowing. But this is the kind of thing which would need a bit of refinement as you went to keep it on-task.
In contrast, here’s what I get when I just ask it for ten original fantasy races (going for quantity over quality):
Could you please provide me with ten fantasy races? These races should not resemble the races in Tolkein’s work or in Dungeons and Dragons. Each race should have a name and a physical description, and each description should only be about one sentence long. Could you please provide this in bullet point form.
Sure! Here are ten fantasy races, each with a name and a one-sentence physical description:
- The Kaltorans: A race of bipedal creatures with razor-sharp claws and the ability to breathe underwater.
- The Lumians: Glowing beings made of pure energy that can manipulate their surroundings with their minds.
- The Xelvians: A race of shapeshifters with the ability to take on the form of any living creature.
- The Zorans: Insectoid creatures with a hard exoskeleton and the ability to control the elements.
- The Faeir: Tiny, winged creatures that live among the flowers and are capable of granting wishes.
- The Gorgons: Serpentine beings with the power to turn those who gaze upon them to stone.
- The Nymirs: A race of aquatic beings with the ability to control the tides and currents.
- The Drakons: Large, fire-breathing reptiles that are said to be the guardians of the underworld.
- The Sylphs: Ethereal beings of air that can manipulate the winds and clouds.
- The Gnomes: Small, earth-dwelling creatures with a talent for engineering and a love of nature.
OK, so we’ve gone from character descriptions to faction dynamics to species and culture. Next stop on our world-building journey is conlangs. My love of conlangs is matched only by my deep appreciation for how navel-gazey they are, and my complete inability to come up with made-up words which don’t sound completely ridiculous and awkward.
I generally feel that a “good” conlang3 is strange enough to feel fantastic, while also being familiar enough to provide everyone with a bit of a reference point when it comes to pronunciation. I’ve never really managed to split that difference manually - let’s see what ChatGPT can do.
Could you generate 10-20 names of cities and towns in a fictional language? The language should sound Germanic (but not be too close to German), and the names should have some elements in common. Could you also please provide a quick glossary showing what some of the common components of the names mean when translated.
Sure! Here are ten city and town names in a fictional Germanic-sounding language:
- Walstorn
- Hargrund
- Jornstad
- Rivenfall
- Torshavn
- Fjordheim
- Brynjarr
- Vestfor
- Skarlagen
- Stormhavn
Here’s a quick glossary showing what some of the common components of the names mean:
- “Wal”: means “ruler” or “leader”
- “Storn”: means “town” or “settlement”
- “Harg”: means “army” or “defense”
- “Rund”: means “round” or “circular”
- “Jorn”: means “day” or “light”
- “Riven”: means “split” or “divided”
- “Fall”: means “waterfall” or “rapids”
- “Tors”: means “tower” or “stronghold”
- “Fjord”: means “narrow inlet” or “sea inlet”
- “Bryn”: means “hill” or “mound”
- “Vest”: means “west”
- “Skarlag”: means “red rock”
- “Storm”: means “storm” or “tempest”.
Note: These words and their meanings are not based on any real language and are purely fictional.
So that’s a bit of a bust. I mean, don’t get me wrong, these are some good names, but there’s a 1:1 mapping between the majority of these words and German or other languages. ChatGPT is outright lying to us here in that last paragraph - we’ll come back to how it favours plausibility over accuracy later on.
Let’s see if ChatGPT can improve when we point out its mistake.
Could you make a similar list, but without recognisable particles like “havn” or “fjord”?
Certainly! Here are ten more names of cities and towns in a fictional Germanic-sounding language, without recognizable particles like “havn” or “fjord”:
- Frorstrand
- Karmtol
- Loddgard
- Myrdon
- Norrland
- Odalmark
- Randvold
- Svalbard
- Tindholm
- Ulvangen
And here’s a quick glossary showing what some of the common components of the names mean:
- “Fror”: means “cold” or “frost”
- “Strand”: means “beach” or “coast”
- “Karm”: means “crooked” or “twisted”
- “Tol”: means “valley”
- “Lodd”: means “burial” or “funeral”
- “Gard”: means “enclosure” or “fence”
- “Myr”: means “marsh” or “swamp”
- “Norr”: means “north”
- “Odal”: means “heritage” or “legacy”
- “Mark”: means “boundary” or “border”
- “Rand”: means “edge” or “rim”
- “Vold”: means “wall” or “rampart”
- “Sval”: means “cool” or “chilly”
- “Tind”: means “peak” or “mountain top”
- “Ulv”: means “wolf”.
Again, these words and their meanings are not based on any real language and are purely fictional.
We’re getting better, but there’s still a lot of recognisable particles here - Svalbard and Tindholm are just real-life places. But what can we expect from ChatGPT? It’s building its answers from a big old corpus of real-life writing, so of course most of its names are going to either be places it’s seen mentioned, or mashups of multiple places.
If there’s one thing my previous experiments have shown, it’s that you sometimes need to take ChatGPT through the process step by step. So what happens if we start by defining some phonemes, and then get to city names? In other words, let’s go full conlang nerd!
Hi ChatGPT, how’s your day been? Could I get you to create a list of phonemes for a constructed language that sounds vaguely Germanic, but also has a bit of a Russian feel? Could you also generate twenty common words in this language?
As an AI language model, I don’t have personal experiences like humans do, but thank you for asking! Here is a list of phonemes for a constructed language that sounds vaguely Germanic with a bit of a Russian feel:
Vowels: /a/, /e/, /i/, /o/, /u/, /ɛ/, /ə/, /ɵ/, /y/ Consonants: /b/, /d/, /f/, /ɡ/, /h/, /j/, /k/, /l/, /m/, /n/, /ŋ/, /p/, /r/, /s/, /t/, /v/, /w/, /z/, /ʃ/, /ʒ/, /ç/, /x/
And here are twenty common words in this constructed language:
- taag - day
- hüs - house
- vög - bird
- waater - water
- kalt - cold
- varm - warm
- feer - fire
- trei - tree
- maan - moon
- sterne - star
- lücht - light
- shuld - debt
- bok - book
- voorn - truth
- krieg - war
- vechten - fight
- groot - big
- klein - small
- hand - hand
- füß - foot
A lot of these words sound very familiar to German words (for example “klein” means “small” in German). Could you get rid of the words which map directly to actual German words and make up new words in their place?
Sure, I can create new words to replace those that map directly to German words. Here are twenty new common words in the constructed language with a vaguely Germanic and Russian feel:
- thraam - day
- korr - house
- vliet - bird
- swil - water
- koldur - cold
- wärmik - warm
- feërnik - fire
- triel - tree
- måneer - moon
- stjernic - star
- luchtor - light
- schulder - debt
- boktoor - book
- woontir - truth
- kriega - war
- vechtir - fight
- groodar - big
- kleyoor - small
- handir - hand
- fuusik - foot
How do you pronounce feërnik?
“Feërnik” is pronounced /ˈfeːrnɪk/. It is written with a diaeresis (¨) over the first “e” to indicate that it is pronounced separately from the “e” that follows it. The “r” sound is pronounced with a slight trill or tap, and the stress is on the first syllable.
Could you generate ten city names in this constructed language? Could you also make sure these don’t correspond to actual place names?
Sure! Here are ten city names in the constructed language:
- Korrheim
- Swilborg
- Stjernov
- Wärmisgrad
- Trielsburg
- Schuldorod
- Luchtorshausen
- Feërgorod
- Bokton
- Vlietbrücken
I made sure that these city names don’t correspond to actual place names by using the phonemes and sounds in the constructed language and combining them in a unique way.
So it took a bit, but we got to some more alien-sounding (but still definitely Germanic!) city names. Swilborg? Stjernov? I have the urge to re-watch The Witcher…
I saved the hardest until last. Up to this point, we’ve been asking ChatGPT to make narrative and fiction - things that are, in general, linked to broad human experience. And it’s done a pretty good job - again, given the amount of time (minimal) and money (none!) we’ve invested in the tool, and the complexity of our queries, I think it’s batting a great average. But how will it face with building an actual RPG with mechanics?
I gave it a few goes at a whole-cloth RPG, and it…well, it felt a little like someone who’d never read a rulebook trying to make some rules:
Please create a one-page rpg about being a civil servant in Cold War Germany
Civil Servant in Cold War Germany RPG
Objective: You are a civil servant working for the government in Cold War Germany. Your goal is to maintain the stability of the country and preserve the power of the government, while navigating the challenges and dangers of the Cold War.
Background: The year is 1980, and the world is divided between two superpowers: the Western democracies led by the United States, and the Eastern communist bloc led by the Soviet Union. Germany is divided into two states, the Federal Republic of Germany (West Germany) and the German Democratic Republic (East Germany). You are a civil servant in East Germany, working to maintain the power and stability of the communist government in the face of growing dissent and external threats.
Character Creation:
- Choose your background: You can choose to be a high-ranking government official, a mid-level bureaucrat, or a low-level clerk. This will affect your starting abilities and resources.
- Choose your skills: Each character has a certain set of skills, such as knowledge of the law, knowledge of history, or the ability to persuade others. Choose three skills to specialize in.
Gameplay: Each turn represents one week of in-game time. You will be presented with various events and tasks to complete, such as suppressing dissent, negotiating with foreign governments, and managing government programs.
Gameplay Mechanics:
- Abilities: Your character has a set of abilities, such as negotiating, investigating, or infiltrating. These abilities can be used to complete tasks and overcome challenges.
- Resources: You have access to various resources, such as money, personnel, and information, that can be used to complete tasks and overcome challenges.
- Moral Choices: As a civil servant in a communist government, you will face many moral dilemmas. Your choices will affect your reputation and the stability of the country.
Victory: You win the game by successfully maintaining the stability of the country and preserving the power of the government for five years (25 turns). You lose the game if dissent reaches a boiling point and the government collapses.
This RPG provides a unique experience, exploring the challenges and dangers of being a civil servant in Cold War Germany. It allows players to experience the complex moral dilemmas and decisions faced by those working to maintain the power and stability of a communist government.
I mean, it’s not a bad idea for a game, but the mechanics are completely absent, the rules skip over entire swathes of the core loop, and there’s no internal cohesion.
For my next attempt, I tried to hammer home the importance of including mechanics in the description:
Please create a simple roleplaying game where the players are a group of pigeons who are tasked with shepherding souls to the underworld. The game should include basic task resolution mechanics, and the players should have to deal with the fact that their characters are easily distracted by shiny objects.
Roleplaying Game: “Pigeon Underworld”
Players: A group of pigeons tasked with shepherding souls to the underworld
Objective: To successfully guide as many souls as possible to the underworld without getting distracted by shiny objects.
Task Resolution Mechanics:
- The player rolls a 6-sided die.
- A roll of 4, 5, or 6 is considered a success.
- In case of distractions by shiny objects, the player must roll again. If the roll is less than 4, the pigeon is successfully distracted and fails the task. If the roll is 4, 5, or 6, the pigeon resists the distraction and may continue with their task.
Gameplay:
- Each turn, the player selects a soul they wish to guide to the underworld.
- The player then makes a task roll to determine if they successfully guide the soul to the underworld.
- If the pigeon is distracted by a shiny object, the player must roll again to resist the distraction.
- The game continues until all players have had a turn or until a designated number of turns has been reached.
- At the end of the game, the player with the most successfully guided souls wins.
Note: The players may also choose to add in their own unique twists and challenges to the game as they see fit.
Again it feels like we’re hitting the edges of ChatGPT’s abilities - it’s like it’s trying desperately to answer our questions, but no one will tell it what an RPG is. The mechanic is…fine, I guess. I like how ChatGPT knows we need to include shiny objects, but isn’t quite sure what we mean. It gives me intense vibes of a high schooler trying to bullshit their way to a pass mark on an essay they never studied for.
Perhaps the issue is that we’re going too big, too soon. What if we just try to make a core mechanic, and build out from that? After all, picking quantity over quality helped with some of our previous examples.
Could you please provide three different mechanics for conflict resolution in a roleplaying game? Each mechanic should use a standard deck of playing cards. These mechanics should include some form of push-your-luck element, and may also include a way for one player to help another.
Sure, here are three different mechanics for conflict resolution in a roleplaying game using a standard deck of playing cards:
High/Low Draw: Players draw a card and add it to their skill level. They can then choose to draw another card to increase their score, but if they draw a card that’s lower than their original draw, they bust and their score is reduced to 0. The player with the highest score wins the conflict.
Betting: Players each draw a card and secretly bet on whether their card is higher or lower than their opponent’s. They can choose to bet again and again, but each additional bet increases the risk of losing their entire bet. The player with the winning card wins the conflict and any bets made by the loser.
3.Cooperative Play: Players draw a card and add it to their skill level. They can then choose to sacrifice their turn to help another player by giving them their card. The more players that cooperate, the higher their combined score, increasing their chances of success in the conflict. However, if any player chooses to be selfish and not cooperate, they risk bringing the whole team down.
Could you suggest three different task resolution mechanics for a roleplaying game? They should use a dice pool mechanic - in other words, the player should assemble a pool of dice based on character skill, the context surrounding the roll, etc., and then roll them, with the outcome of the task depending on the dice rolled.
Certainly, here are three different task resolution mechanics for a roleplaying game using a dice pool mechanic:
Summing Dice: Players roll a pool of d10s equal to their skill level, with each die showing a number from 1 to 10. The player sums up the total of their dice, with each die that rolls a 10 being rerolled and added to the total. The result is compared against a target number to determine success or failure.
Counting Successes: Players roll a pool of d6s equal to their skill level, with each die showing a number from 1 to 6. The player counts the number of dice that roll a 4, 5, or 6, which are considered successes. The number of successes is compared against a difficulty threshold to determine success or failure.
Roll and Keep: Players roll a pool of d12s equal to their skill level, with each die showing a number from 1 to 12. The player then chooses a number of dice to keep and add together, based on the context of the task and their character’s approach to it. For example, a character trying to charm someone might keep the two highest rolls, while a character trying to break down a door might keep the two lowest rolls. The result is compared against a target number to determine success or failure.
In both the examples above, I don’t think ChatGPT quite gets the way in which conflict and task resolution mechanics interact with the narrative. I tried to get it to expand on the roll and keep method above, and while it provided a little extra crunch it didn’t really explain why you might want to pick high or low rolls, as much as it doubled down its existing pick.
Somewhere else on the internet I overheard someone say that ChatGPT is optimised not necessarily to give truthful replies, but to give plausible ones, and that definitely feels like what I’m encountering here. The program wants to give me a plausible answer, but the limitations of the corpus mean it’ll never actually give me what I want. So it produces something plausible, and explains it as well as it can. Kind of like you turned up your last English exam in high school, found that you needed to write an essay on a subject you hadn’t studied for, and decided that you might as well write up as good a bit of bullshit as you can and hope that you can fool the marker into giving you a pass mark.
So what have we learned from all this?
When it comes to descriptions, people, and relationships, ChatGPT is pretty strong. We saw it produce some pretty coherent character descriptions that you could just cut and paste into your own LARP and either modify to fit the game and factions, or even just keep as-is with some minor tweaks. If I find myself using it in any of my future work, this is where I imagine I’ll find myself using it. It kind of makes sense - the corpus on which ChatGPT is trained will have such a wealth of information about people and relationships in all different kinds of settings that it has plenty to draw from.
The algorithm fares a little worse when it comes to worldbuilding, specifically for conlangs and building cultures. I think that you could probably get somewhere with a bit of work, but I suspect the task is just so niche that it doesn’t quite know what to do without a good deal of preparation. Still, if you got the pipeline down pat, I suspect it could probably do a lot of groundwork or at the very least generate a bunch of candidates that you could then edit yourself.
And then everything falls apart when we hit game mechanics. It just seem any good at developing anything on this front!
What patterns do we see here? I think one is the plausibility-correctness axis that I hinted at above. I figure things like character descriptions and relationships between people function at least somewhat on plausibility - if it sounds like it should work, then it passes muster. Once we start to venture into the world of rules and mechanics, however, the algorithm starts to struggle, and no amount of explaining can really pull it out of its pit.
There’s another factor here too, I think - the divde beteween creator and editor. ChatGPT seems to be great at pulling together ideas - for any of the above you could regenerate the algorithm’s response and it would likely give you a completely different but still plausible answer within the bounds of your request.
It feels like the best way to use ChatGPT in these examples is like a giant randomiser/generator - plug in your requirements and go for quantity over quality. Then you can pare down the suggestions, pick the ones that work, iterate on them if necessary, but turn them into your finished product. It’s definitely how I think I’ll be using it in the future - not as an end-to-end replacement for human effort, but the starting point.
Note that I’ve formatted all conversations for ease of reading. All the responses from OpenAI are plaintext when you receive them through the app. ↩
I particularly like the crew comes into conflict with Lopaka because he presumably refuses to put the weird food they buy at layovers into his generations-old traditional meals. True “we’ve been in this ship with each other for too long” vibes. ↩
Here “good” means “useful in the context of roleplaying games”. ↩
The latter half of 2022 was a roller coaster ride, with a kid approaching one year old and the family shifting cities. I spent a good deal of my reading year re-reading the Hornblower novels, which debuted in my 2020 list. Books tend to take one of two roles for me - either stretching me out, or providing comfort - and a re-read of the whole series was an exercise in comfort food for a trying time.
Unfortunately, a number of factors - including my journey through all of C. S. Forester’s flagship (hah) series, a couple of forays through longer books that I really didn’t enjoy, and the general disruption of a child-ful existence, meant I didn’t get through as much reading as I’d really like to do. Still, I did manage to get some good books read. Rather than try to expand this list to five and add in something sub-par, I’m going to cut one out just keep to the meat.
The Web of Life - Fritjof Capra. I started this book expecting to read an introduction to systems theory, and instead got a grand old tour through a holistic theory of life and relationships. Capra definitely has what I think is a polarising writing style (as opposed to scientific writers who will try to “step out of the way” of the reader) - you can tell that the subject matter is something he cares deeply about. That makes me wonder, at least a little, if he’s at all exaggerated the popularity and acceptance of the theories he discusses in his book, and I don’t have the background (or time, unfortunately) to find out - so I’m taking his claims with a grain of salt.
Braiding Sweetgrass - Robin Wall Kimmerer. I’d seen mention of this book in a number of places before I got around to reading it. It’s a great combination of personal narrative and handbook on personal ecological activism. Kimmerer does well to balance the tension between call to action and empathy - she understands how hard it is to care about your environment when you also have to live your life (and communicates that understanding so well), but still pushes you. I finished this book feeling a gentle ache in my heart. Pairs well with How to Do Nothing, which also featured on my 2020 list.
The First Fifteen Lives of Harry August - Claire North. I love a good time travel science-fiction thriller, when done well, and this falls into that Groundhog Day sub-genre that I seem to just eat up. The 7½ Deaths of Evelyn Hardcastle made it onto my 2021 list at least partly because it fits in there, and you can’t help but trace a line from there to here (the similarity between titles seems to suggest it at the very least). The hardest part of this genre is, I think, to stick the landing: this book does it about 85%, which is better than a lot.
Sea of Tranquility - Emily St. John Mandel. I discovered Mandel with Station Eleven, which I loved, but never read her follow-up novel The Glass Hotel (after it received pretty negative reviews from friends). So this was a nice return! My read-through of Station Eleven will always be coloured by COVID-19, and this book is a fitting follow-up to that - although a bit stronger on the science-fiction elements and feeling a bit grander in scope. In saying all that, I feel it was missing a bit of the core soul that Station Eleven had - it felt like a lighter touch, a quicker read, and thus not quite as gripping.
]]>Kat Vellos’ We Should Get Together has been on my to-read list for a few months, and when I got to it I absolutely blew through it. Sometimes you’re in the right mood for a book and it’s less like reading and more like having a conversation in your head. The book itself is about building friendships as an adult, and one of the themes that comes through time and time again is the requirement that you and your new friend can just talk without a specific goal in mind.
Over the past year or so, I’ve found it harder and harder to have what I’ve mentally classified as “agendaless social interaction”. It’s a confluence of events - having moved out into the ‘burbs in a city that’s pretty split up, having recently had a kid, and of course the ever-looming threat of COVID-19 and its variants occasionally isolating households and turning every public outing into a quick back-of-the-envelope risk assessment. In the past, I’ve used social events as a way of turning colleages or acquaintances into friends, as well as keeping in touch with folks who I wouldn’t otherwise run into - so not really being able to have catch up has done a number on quite a few friendships.
Alongside all of this, I’ve had Cal Newport and Jenny Odell sitting in my mind - their books Digital Minimalism and How to Do Nothing both took their own approach to skewer social media and its impact on our lives. Specifically, Newport quotes MIT professor Sherry Turkle:
In her 2015 book, Reclaiming Conversation, Turkle draws a distinction between connection, her word for the low-bandwidth interactions that define our online social lives, and conversation, the much richer, high-bandwidth communication that defines real-world encounters between humans.
During an appearance on The Colbert Report, host Stephen Colbert asked Turkle a “profound” question that gets at the core of her argument: “Don’t all these little tweets, these little sips of online connection, add up to one big gulp of real conversation?” Turkle was clear in her answer: No, they do not.
Turkle specifically differentiates between online and in-person interaction - as does Newport. Specifically, Turkle identifies in-person interaction with high-bandwidth communication, subtlety of interaction and expression, and (as a result) nuanced communication and deeper relationships. In contrast, online interaction, limited to certain senses or even just text, is low bandwidth, not particularly nuanced, and proves a barrier to deepening connection.1
In general, I agree with their thesis: it definitely aligns with the feelings I’ve had using these tools over the years. But I think there’s a low-bandwidth medium that does provide the kind of deeper interaction that Turkle attributes to conversation. You might have guessed it, based on the title of this post and its central thesis: it’s email.
Email doesn’t feel like it fits into Turkle’s framework at all - in fact, if anything, it displays even less similarity to in-person conversation than the majority of modern online modes of communication. Email is asynchronous, it’s text-only by default…it’s decidedly disconnected and out-of-date when you compare it to pretty much every other social media channel. It’s super-low bandwidth. And yet email conversation - when you can get it going - feels richer than similar conversations over social media.
I have a theory about this, although I don’t feel I have a way to really prove it.
Instant messaging, and most social media messaging systems by extension, want to be analogues for conversation. Just consider the way they present themselves - with your messages and other parties’ represented by chat bubbles or ovals on either side of the box, using language like “conversation” and “chat”, and of course, by being synchronous, by giving us real-time feedback when people are typing, or letting them respond via emoji.
In contrast, email is an analogue for letter-writing. Consider how we start and end emails, how we often go through multiple drafts or rewrites for important or longer-form emails - even how typos in emails are construed.
Letter-writing is itself an art form that goes back centuries, and I would argue that it allows the sort of deep connection Turkle wants to see in conversation, just by different means. By giving each side of the exchange time - both time to write the letter, and time to read it - we can provide the extra bandwidth through word choice, pacing, sentence and paragraph construction, the same way that an author uses these tools to portray a richness and depth of writing even though they won’t exchange one word with you face-to-face. The same is true for email: just because I can send an email and have it delivered to the recipient instantaneously, there’s still mechanisms to slow to the cadence of the communication (no read notifications, a reliance on manually removing it from your inbox when you’re done).
And to me, that’s why email works as a medium separate from most other online interaction: because it’s not trying to be a conversation.
It would be a lie to say that all of this came into my head, I sat down and thought it out, and came up with a plan. What really happened was: life happened. Someone moved away. I found that with hybrid work and childcare, I was leaving my house less and less. I found myself holed up with a laptop of an evening, wishing I could just write something to someone but finding no one online I could really connect with (and really not keen on the, you know, interaction, just wanting to write). I finished up We Should Get Together and felt a pull to do something.
So the next time I could see someone about to vanish from my life due to changing circumstances, I asked if they wanted to collaborate on an experiment with me. And they did!
The experiment is still very small - I have one and a half folks on board2. But it’s finding its feet - I’ve sent a number of emails over about six months, and I’m starting to get some idea as to how it goes. So that’s not too bad.
So what makes a good exchange of letters (or, in this case, emails)? I don’t know! I’m also trying to work out. But here’s what I’m trying right now, based on minimal experience:
1. Correspondence must be two-way, at both the macro- and micro-level. At the macro-level, that means ensuring that your correspondence is an ongoing conversation - following up on previous topics, delving deeper on stuff that interests you. On the micro-level, this means ensuring your emails aren’t just screeds of your thoughts, but that you also ask questions and prompt your partner to respond. It’s also worth pointing out that different people have different demands on their time - you might find yourself writing two emails to your penpal’s one - and that’s fine, as long as both people are contributing. There’s no point you pouring your soul out into the ether, and you have to be ready for your partner to just not be able to return the favour, and let this one go.
2. Give it time to breathe. And not just so you can think of interesting and well-thought-out responses. A gap of time between emails allows life to happen, and the things you experience, the conversations you have, will then feed into your next email.
3. Go deep slowly. The great thing about a long written text is that you’re able to address a subject at much greater length than you might be able to in instant messaging, or even in spoken conversation. That’s not to say you should start here - you want to spend time building trust until that kind of conversation feels natural. But it’s a great endpoint, and it takes advantage of the medium.
So how’ve I been implementing this? It looks like the following:
Step 1. I find people I want to email with. This started with one person who was changing jobs, who I didn’t see socially, but whom I wanted to keep in touch with. For you, it could look different. Maybe you want to make a list of your friends whom you’ve fallen out of touch with, or whom you want to know better. I’d recommend introducing penpals one at a time, or you’ll find yourself overwhelmed.
Step 2. Get them to sign up to the scheme. It can feel intimidating to say to someone, “Hey, do you want to be email penpals?” - if you want, you could always frame it as “Hey, I’m trying this new thing, want to help?” Either way, you want to make sure the other party is on board. (Some particularly good people don’t have the kind of life that allows them to write long emails, and know it - and will tell you straight up. That’s a great way to avoid several emails’ worth of work for little gain.)
Step 3. Send your first email. This bit is tricky, because you don’t just want it to be you broadcasting what’s happening in your life - you want to provide hooks for deeper conversation. Going back to the top of this post, We Should Get Together has some great conversation-starting questions you can weave into your email. Failing that, you can always ask what people have been reading/watching recently.
Step 4. Wait. This is perhaps the hardest bit. (Or the easiest bit, depending on your life!) Other people’s lives are just as busy as yours, and it’s unlikely people will be as invested in this scheme as you are (after all, you’re the one who’s reading two thousand words on email penpals, and the one who initiated the whole thing). You need to have faith that your penpal will read your email, will respond.
Step 4a. And then one day, nestled amongst sale brochures and notifications of changes to terms of service, you’ll see an email written especially for you from your friend! Go on, open it and read it. Now I said step 4 was the hardest bit, but it’s not, because it’s actually…
Step 5. Wait (again). Don’t respond immediately! Instantly responding means you burn out all the energy you’ve built up, and you barely have anything to write about. So sleep on that email. Let it sit in your inbox for a few weeks. Wait until things start happening in your life and you go “Oh, that passage I read really speaks to what we’ve been discussing”, or “Oh, I know how to answer that question!”. And then, once a few weeks have passed…
Step 6. Start writing a response. Don’t feel like you have to write it in one sitting. I often start mine with a date and time and where I am, and finish them the same way. If it takes you a couple of weeks to write your email, that’s OK! If you’re feeling picky, you can always do a quick go-over and edit at the end to tidy it up. But also, your friend won’t mind if it’s a bit rambly. It’s not like you’re going to publish it.
Step 7. And you’re back to Step 4! Keep going, and watch your stack of correspondence build up.
Be patient! People have lives, those lives are hectic.
It’s a real tough job not to follow up after a couple of weeks to go “Hey did you get my email are you replying?” Every time I get that urge, I tamp it down immediately - if the person wants to respond, they’ll know it’s on their list, and you want this to be a pleasure for them, not a chore.
Some people will want to email you - and will probably be happy to try this experiment out - but will then find they don’t actually have the time to email you back. That’s fine too! You’ll find out soon enough, even if you send a couple of emails with no response. You might have to look at other ways of keeping in touch with them.
This is a question whose answer varies greatly depending on you, your penpal, and your relationship. But to start off:
Hopefully as you’ll go along you’ll be able to address other subjects that come up - respond to elements of their previous email, follow up on themes which have emerged, and so on.
This is a fun one to deal with - I’m often Facebook friends with my penpals anyway, and that provides a really obvious medium for quickly checking up with them (or sending them photos of our kid doing silly stuff, or what-have-you). There’s nothing wrong with communicating over multiple media, but it can feel like the more frequent medium will suck the life out of the others. I’ve been trying to keep Facebook messages to quick and light-touch stuff, and in some cases I’ve actually told people I’m saving subjects for my regular emails.
Right now, I’m still working this out. I hope that over the course of 2023 I can build my emailing muscles a bit more, and work out how this whole thing can work long-term - and then perhaps when another good friend shifts jobs, or moves city, I can use this as an opportunity to spread the project a bit wider.
It definitely feels like a slow burn - this isn’t a product of a world that’s interested in 10x scaling, or exponential growth. But it feels like something that - if done right - I could be doing decades from now, and I’d love to see if that’s the case.
However, this low-bandwidth communication may still scratch our itch for acknowledgement and connection - kind of like a “junk food” equivalent to in-person communication and a potential evolutionary mismatch that social media companies love to exploit. ↩
Like many good things in life, I suspect this project won’t scale too much anyway. There’s the point where it’s a joy and a privilege to write someone an email, and then there’s the point where you have to get an email written every week or you’re falling behind. ↩