19 September 2023 to 27 April 2018
I read a lot of other people's writing about streaming and music, in the press and in books and on Twitter (or its scattered mirror-shards), and I almost always end up annoyed that the story is most consistently told from the point of view of an outsider with speculative information and dour grudges. There are occasional exceptions, like Nick Seaver's Computing Taste, but that's a work of anthropological scholarship: a story about stories about our future, not the story itself.
The story, I really believe, is that having all the world's music online together is one of the greatest cultural developments of the internet age. Somebody who both fully understands and emotionally believes in music streaming, I kept muttering, should write that book.
I've been arguing this idea in scattered blog posts and comment threads and talks, already, but I had more spare time than usual during the pandemic, so I started trying to organize the whole story, not the specific business of Spotify or any one company, but the underlying argument for why streaming is good for music and streaming music is good for humanity. I both know and believe enough to explain how the fears it provokes are mostly less scary than they seem, although in some cases also more scary than you might realize, but that either way the joys are even more transformational. I haven't been talking about this during the process, because I wasn't sure how far I'd get, but I wrote it, and an agent found me, and the agent found a publisher, and today the book was announced to the UK trade press, so it's officially unsecret.
It's called You Have Not Yet Heard Your Favorite Song: How Streaming Changes Music. It's not coming out until June 2024, because paper is a slow liquid. I have been blithely accustomed to writing about music online and hitting OK for my entire adult writing life, so this is a series of weird new old experiences for me: writing things and then scrutinizing them repeatedly; having an actual professional editor badger me (kindly) into taking out half of the adverbs and a 20,000-word digression about E.F. Codd; the idea that I still have to wait nine more months before people can read a thing I finished writing months ago.
But, on the other hand, I still like reading books myself, and a 2024 publication date is a heartening gesture of faith that the AI apocalypse will hold off at least that long. So far that faith is scheduled to be expressed in English (complete with "Favourite" in the UK) by Canbury Press, translated into French by Hachette, and into Chinese by ECUS Publishing House. If you have, or are, contacts at publishers of books in other languages, or especially any US publisher interested in handling the American edition, get in touch.
Otherwise, it is not necessary to take any action at this time. Continue with your lives. Listen to music. Read Jon Alexander's excellent Citizens, about the historical shifts in social narratives from subject/rule to consumer/vendor to citizen/community, which was also published by Canbury and isn't about music but isn't entirely unrelated to mine. If you think of ways to share or experience more joy, or less fear, you needn't wait to see if I covered them.
But if you haven't thought of any by next June, maybe my book will be able to help.
Some links as I spot them:
- The announcement was also covered on BookBrunch, but you can't read that without a subscription.
- Amazon UK lists both the ebook and the UK paperback.
- WHSmith lists the UK paperback.
- Amazon US and Barnes & Noble have only the ebook version so far.
- I see the (English) ebook in Austrian, Italian, Japanese, 1 2 Portuguese and 1 2 3 German shops.
In a 2009 post about music-data modeling, I posed the reasonable human question "What Beatles album is 'Day Tripper' on?" and bemoaned the various ways in which all available music-data sources failed to effectively answer it.
My human answer was this:
As of today, ChatGPT's (GPT-3) answer was this:
That's pretty good. Of course, the Wikipedia page for the song has this information, and my original question was about structured data-querying, not summarization of pre-written human text.
The "Day Tripper" thing was also a deliberately simplified test-question, too, because when I tried to write that post using my actual question for testing the existential level of musical question-answering, the narration was unhelpfully complicated. That question was this:
"Who are all the producers who produced non-Big-Country albums that members of Big Country played on?"
I have never had the patience to assemble a decent human answer to that, but I'd still like to read one. So today I asked ChatGPT. Here's what it said:
Points awarded for clarifying that this is not an exhaustive list. Points deducted for failing to clarify that it is not a factual list, either. That is, it does involve or at any rate implicate some facts, but those facts mostly do not connect in the ways described here.
Alan Shacklock was an English producer who moved to Nashville. Big Country singer Stuart Adamson also moved to Nashville at one point, and formed a country duo called The Raphaels. Their one album came out in 2001, not 1993, and was called Supernatural, not The Raphaels. As best I can tell, Shacklock did not produce it, nor any other album named The Raphaels. Tony Butler was Big Country's bassist, but didn't play on Supernatural, and would be the less-good example to pick even if he had, since it was Stuart's band.
Robin Millar produced the Big Country album The Seer, so including him in this list via some other album is not really what I meant, but I didn't clarify that, so I'll allow it. Or I would allow it, except that Justin Currie (better known as the singer in fellow-Scots Del Amitri) has no solo album called Hope and Despair, nor indeed any solo album earlier than 2007, nor any solo album produced by Robin Millar or played on by Big Country drummer Mark Brzezicki, although with Mark I guess it's always possible he participated in disguise or by accident.
Iona is another Scottish band, so one can easily imagine that some connection exists, but Iona's albums are all self-produced by co-founder Dave Bainbridge, none of them are called Bare, none of them came out in 1995, and none of them feature Dave Fielding, who was in The Chameleons but not Big Country for any non-quantum sense of "briefly".
Westworld did release their debut album in 1987, but it wasn't self-titled, wasn't produced by Steve Brown, and probably didn't feature Brzezicki.
The Brian Eno line is the best one in this answer, since it describes an actual album with its actual year and artists, and one of its actual producers. Sadly, Stuart didn't play on it, which is the only reason it's supposed to be in this list, so giving it credit for not introducing ancillary errors is like praising a cook for making cauliflower gratin with only organic red grapes and fresh herring.
I admit that I did ask it for 10 more examples, and if you willingly eat red-grape herrings you can't really complain, so I won't explain all the errors in those. Except to note that Mark Knopfler of Dire Straits definitely did not "co-found" Big Country. I never regarded this question as unanswerable, and having it misanswered doesn't change my feelings. I've always assumed that answering it would be an eventual triumph of conscious data-modeling, not massive ML overtraining, and I think ChatGPT wants, if it "wants" anything, me to at least doubt that now.
Maybe? A little bit? The answers exist, spread out among our minds. Maybe brute-force retro-structuring can eventually extract them from chaos without requiring the chaos to be improved first. I guess ChatGPT wins while losing by the mere fact that it has learned to answer questions "well" enough that we keep asking it things even though the answers are bad. If we are eradicated by this wave of AI, it will certainly be our own fault.
But that was always going to be true. Our self-created dooms always have the same ingredient.
My human answer was this:
This is partially a trick question, of course, as "Day Tripper" was originally a non-album single, but it has been on several Beatles compilations over the years, including the red 1962-1966 best-of, and in the remastered 2009 catalog it lands on both the mono and stereo versions of Past Masters.
As of today, ChatGPT's (GPT-3) answer was this:
"Day Tripper" is a single released by The Beatles in 1965, along with the song "We Can Work It Out". Although it was not included on any of The Beatles' original studio albums, it was later released on several compilation albums, including the "1962-1966" (also known as the "Red Album") and "Past Masters" compilations.
That's pretty good. Of course, the Wikipedia page for the song has this information, and my original question was about structured data-querying, not summarization of pre-written human text.
The "Day Tripper" thing was also a deliberately simplified test-question, too, because when I tried to write that post using my actual question for testing the existential level of musical question-answering, the narration was unhelpfully complicated. That question was this:
"Who are all the producers who produced non-Big-Country albums that members of Big Country played on?"
I have never had the patience to assemble a decent human answer to that, but I'd still like to read one. So today I asked ChatGPT. Here's what it said:
Here are some producers who worked on non-Big Country albums that featured members of the band:
Alan Shacklock: Produced the album "The Raphaels" (1993), which featured Tony Butler on bass guitar.
Robin Millar: Produced the album "Hope and Despair" (1994) by Justin Currie, which featured Mark Brzezicki on drums.
Mike Thorne: Produced the album "Bare" (1995) by the band Iona, which featured Dave Fielding (who had briefly played guitar for Big Country) on guitar.
Steve Brown: Produced the album "Westworld" (1987) by the band Westworld, which featured Mark Brzezicki on drums.
Brian Eno: Produced the album "Apollo: Atmospheres and Soundtracks" (1983) by Brian Eno with Daniel Lanois and Roger Eno, which featured Stuart Adamson on guitar.
Again, this is not an exhaustive list, but it includes some notable examples of producers who worked on albums that featured members of Big Country in a different musical context.
Points awarded for clarifying that this is not an exhaustive list. Points deducted for failing to clarify that it is not a factual list, either. That is, it does involve or at any rate implicate some facts, but those facts mostly do not connect in the ways described here.
Alan Shacklock was an English producer who moved to Nashville. Big Country singer Stuart Adamson also moved to Nashville at one point, and formed a country duo called The Raphaels. Their one album came out in 2001, not 1993, and was called Supernatural, not The Raphaels. As best I can tell, Shacklock did not produce it, nor any other album named The Raphaels. Tony Butler was Big Country's bassist, but didn't play on Supernatural, and would be the less-good example to pick even if he had, since it was Stuart's band.
Robin Millar produced the Big Country album The Seer, so including him in this list via some other album is not really what I meant, but I didn't clarify that, so I'll allow it. Or I would allow it, except that Justin Currie (better known as the singer in fellow-Scots Del Amitri) has no solo album called Hope and Despair, nor indeed any solo album earlier than 2007, nor any solo album produced by Robin Millar or played on by Big Country drummer Mark Brzezicki, although with Mark I guess it's always possible he participated in disguise or by accident.
Iona is another Scottish band, so one can easily imagine that some connection exists, but Iona's albums are all self-produced by co-founder Dave Bainbridge, none of them are called Bare, none of them came out in 1995, and none of them feature Dave Fielding, who was in The Chameleons but not Big Country for any non-quantum sense of "briefly".
Westworld did release their debut album in 1987, but it wasn't self-titled, wasn't produced by Steve Brown, and probably didn't feature Brzezicki.
The Brian Eno line is the best one in this answer, since it describes an actual album with its actual year and artists, and one of its actual producers. Sadly, Stuart didn't play on it, which is the only reason it's supposed to be in this list, so giving it credit for not introducing ancillary errors is like praising a cook for making cauliflower gratin with only organic red grapes and fresh herring.
I admit that I did ask it for 10 more examples, and if you willingly eat red-grape herrings you can't really complain, so I won't explain all the errors in those. Except to note that Mark Knopfler of Dire Straits definitely did not "co-found" Big Country. I never regarded this question as unanswerable, and having it misanswered doesn't change my feelings. I've always assumed that answering it would be an eventual triumph of conscious data-modeling, not massive ML overtraining, and I think ChatGPT wants, if it "wants" anything, me to at least doubt that now.
Maybe? A little bit? The answers exist, spread out among our minds. Maybe brute-force retro-structuring can eventually extract them from chaos without requiring the chaos to be improved first. I guess ChatGPT wins while losing by the mere fact that it has learned to answer questions "well" enough that we keep asking it things even though the answers are bad. If we are eradicated by this wave of AI, it will certainly be our own fault.
But that was always going to be true. Our self-created dooms always have the same ingredient.
¶ A short essay about long playlists of short tracks of rain noises and streaming-music economics. · 24 September 2021 essay/tech
Rolling Stone published this recent story (https://www.rollingstone.com/pro/features/spotify-sleep-music-playlists-lady-gaga-1223911/) about the streaming success of the sleep-noise artist/label/scheme Sleep Fruits, who chop up background rain-noise recordings into :30 lengths to maximize streaming playcounts.
Sleep Fruits is undeniably and intentionally exploiting the systemic weakness of the industry-wide :30-or-more-is-a-play rule, as too are audiobook licensors who split their long content into :30 "chapters". The :30 thing is a bad rule. Most of the straightforward alternatives are also bad, so it wasn't an obviously insane initial system design-choice, but this abuse vector is logical and inevitable.
The effect of the abuse for the label doing it is simple: exploitative multiplication of their "natural" streams by a large factor. x6 if you compare it to rain noise sliced into pop-song-size lengths.
The effect on the rest of the streaming economy is more complicated. More money to Sleep Fruits does mean less money to somebody else, at least in the short term.
Under the current pro-rata royalty-allocation system used by all major subscription streaming services (one big pool, split by stream-share), the effects of Sleep Fruits' abuse are distributed across the whole subscription pool. The burden is shared by all other artists, collectively, but is fractional and negligible for any individual artist. In addition, under pro-rata if an individual listener plays Sleep Fruits overnight, every night, it doesn't change the value of their "real" music-listening activity during the day. Those artists get the same benefit from those fans as they would from a listener who sleeps in silence.
Under the oft-proposed user-centric payment system, in which each listener's payments are split according to only their plays, Sleep Fruits' short-track abuse tactic would be less effective for them. Not as much less effective as you might think, because the same two things that inflate their overall numbers (long-duration background playing + short tracks) inflate their share of each listener's plays. But less, because in the pro-rata model one listener can direct more revenue than they contributed, and in the user-centric model they can't.
In the user-centric model, though, if an individual listener listens to Sleep Fruits overnight, that directly reduces the money that goes to their daytime artists. Where pro-rata disperses the burden, user-centric would concentrate it on the kinds of artists whose fans also listen to background noise. This is probably worse in overall fairness, and it's definitely worse in terms of the listener-artist relationship, which is one of the key emotional arguments for the user-centric model.
The interesting additional economic twist to this particular case, though, is that sleeping to background noise works very badly if it's interrupted by ads. Background listening is thus a powerful incentive for paid subscriptions over ad-supported streaming. (Audiobooks similarly, since they essentially require full on-demand listening control.) So if Sleep Fruits drives background listeners to subscribe, it might be bringing in additional money that could offset or even exceed the amount extracted by its abuse. (Maybe. The counterfactual here is hard to assess quantitatively.)
And although the :30 rule is what made this example newsworthy in its exaggerated effect, in truth it's probably not really the fundamental problem. The deeper issue is just that we subjectively value music based on the attention we pay to it, but we haven't figured out a good way to translate between attention paid and money paid. Switching from play-share to time-share would eliminate the advantage of cutting up rain noise into :30 lengths, but wouldn't change the imbalance between 8 hours/night of sleep loops and 1-2 hours/day of music listening. CDs "solved" this by making you pay for your expected attention with a high fixed entry price, which isn't really any more sensible.
I don't think we're going to solve this with just math, which disappoints me personally, since I'm pretty good at solving math-solvable things with math. But in general I think time-share is a slightly closer approximation of attention-share than play-share, and thus preferable. And rather than trying to discount low-attention listening, which seems problematic and thankless and negative, it seems more practical and appealing to me to try to add incremental additional rewards to high-attention fandom. E.g. higher-cost subscription plans in which the extra money goes directly to artists of the listener's choice, in the form of microfanclubs supported by platform-provided community features. There are a lot of people who, like me, used to spend a lot more than $10/month on music, and could probably be convinced to spend more than that again if there were reasons.
Of course, not coincidentally, I have ideas about community features that can be provided with math. Lots of ideas. They come to me every :30 while I sleep.
PS: I've seen some speculation that Sleep Fruits is buying their streams. I'm involved enough in fraud-detection at Spotify to say with at least a little bit of confidence that this is probably not the case. Large-scale fraud is pretty easy to detect, and the scale of this is large. It's abusing a systemic weakness, but not obviously dishonestly.
Sleep Fruits is undeniably and intentionally exploiting the systemic weakness of the industry-wide :30-or-more-is-a-play rule, as too are audiobook licensors who split their long content into :30 "chapters". The :30 thing is a bad rule. Most of the straightforward alternatives are also bad, so it wasn't an obviously insane initial system design-choice, but this abuse vector is logical and inevitable.
The effect of the abuse for the label doing it is simple: exploitative multiplication of their "natural" streams by a large factor. x6 if you compare it to rain noise sliced into pop-song-size lengths.
The effect on the rest of the streaming economy is more complicated. More money to Sleep Fruits does mean less money to somebody else, at least in the short term.
Under the current pro-rata royalty-allocation system used by all major subscription streaming services (one big pool, split by stream-share), the effects of Sleep Fruits' abuse are distributed across the whole subscription pool. The burden is shared by all other artists, collectively, but is fractional and negligible for any individual artist. In addition, under pro-rata if an individual listener plays Sleep Fruits overnight, every night, it doesn't change the value of their "real" music-listening activity during the day. Those artists get the same benefit from those fans as they would from a listener who sleeps in silence.
Under the oft-proposed user-centric payment system, in which each listener's payments are split according to only their plays, Sleep Fruits' short-track abuse tactic would be less effective for them. Not as much less effective as you might think, because the same two things that inflate their overall numbers (long-duration background playing + short tracks) inflate their share of each listener's plays. But less, because in the pro-rata model one listener can direct more revenue than they contributed, and in the user-centric model they can't.
In the user-centric model, though, if an individual listener listens to Sleep Fruits overnight, that directly reduces the money that goes to their daytime artists. Where pro-rata disperses the burden, user-centric would concentrate it on the kinds of artists whose fans also listen to background noise. This is probably worse in overall fairness, and it's definitely worse in terms of the listener-artist relationship, which is one of the key emotional arguments for the user-centric model.
The interesting additional economic twist to this particular case, though, is that sleeping to background noise works very badly if it's interrupted by ads. Background listening is thus a powerful incentive for paid subscriptions over ad-supported streaming. (Audiobooks similarly, since they essentially require full on-demand listening control.) So if Sleep Fruits drives background listeners to subscribe, it might be bringing in additional money that could offset or even exceed the amount extracted by its abuse. (Maybe. The counterfactual here is hard to assess quantitatively.)
And although the :30 rule is what made this example newsworthy in its exaggerated effect, in truth it's probably not really the fundamental problem. The deeper issue is just that we subjectively value music based on the attention we pay to it, but we haven't figured out a good way to translate between attention paid and money paid. Switching from play-share to time-share would eliminate the advantage of cutting up rain noise into :30 lengths, but wouldn't change the imbalance between 8 hours/night of sleep loops and 1-2 hours/day of music listening. CDs "solved" this by making you pay for your expected attention with a high fixed entry price, which isn't really any more sensible.
I don't think we're going to solve this with just math, which disappoints me personally, since I'm pretty good at solving math-solvable things with math. But in general I think time-share is a slightly closer approximation of attention-share than play-share, and thus preferable. And rather than trying to discount low-attention listening, which seems problematic and thankless and negative, it seems more practical and appealing to me to try to add incremental additional rewards to high-attention fandom. E.g. higher-cost subscription plans in which the extra money goes directly to artists of the listener's choice, in the form of microfanclubs supported by platform-provided community features. There are a lot of people who, like me, used to spend a lot more than $10/month on music, and could probably be convinced to spend more than that again if there were reasons.
Of course, not coincidentally, I have ideas about community features that can be provided with math. Lots of ideas. They come to me every :30 while I sleep.
PS: I've seen some speculation that Sleep Fruits is buying their streams. I'm involved enough in fraud-detection at Spotify to say with at least a little bit of confidence that this is probably not the case. Large-scale fraud is pretty easy to detect, and the scale of this is large. It's abusing a systemic weakness, but not obviously dishonestly.
[I woke up this morning with this almost-fully-formed idea in my mind for what I guess would have been a trailer for the upcoming season of Last Week Tonight.]
We open on a close-up of a newspaper with the banner headline
INAUGURATION TOMORROW
and the subhead
President-Elect Announces National Socially-Distanced Hot Dog Cookout
The newspaper then doubles and flies into both sides of a split-screen.
On the left side, the person holding it puts it down, and we see that it's John Oliver. He nods and goes the refrigerator and gets out a package of hot dogs. As he puts it on the counter, we see that the brand is "Hebrew Multinational". He rummages around in the fridge looking for buns.
On the right side, the person puts the paper down, but the camera follows the paper in a POV manner, and thus we see only a pair of small but chubby and slightly orange hands. The hands go to the fridge. It is mostly empty, except that the door shelves are completely full of Diet Coke bottles (all of which have been partially drunk to different levels), the bottom shelf has some crumpled Big Mac wrappers, and the vegetable drawer has the discarded lettuce from a few dozen burgers. And on a middle shelf there is a single lonely package labeled "MyPillow Tofu Pups". This is crossed out in sharpie and "TrumP SteAks" is written over it. The hands hesitate for several seconds before drooping resignedly and taking out the tofu pups.
On the left, John Oliver's voice says, delightedly, "I'll make some buns!", and he opens a pantry to get out a bag of white flour, and then a cabinet to get a mixing bowl.
On the right a defeated voice just mutters, limply, "buns...". The hands open a pantry-like door, but there's nothing inside except 3 crusty bottles of unrefrigerated ketchup and a single bag of white flour. (If you look closely, this says "power" on it instead of "flour".)
Both sides then show quick montages of dough-making activities.
John Oliver mixes water into the flour with quick motions of a wooden spoon until it starts to stick together, and then dumps it out on a cutting board and kneads it with earnest but tentative motions.
The hands dump some flour directly on the formica countertop, pour a blurp of Diet Coke on it, and then poke at it desultorily.
John Oliver, reading aloud from a recipe, says "Allow dough to rise." Animated clocks appear in the corners of both sides, the cameras both zoom in on the blobs of dough/flour, and the clocks spin through an hour or two without any visual change in either blob. The clocks disappear and the cameras zoom back out.
On the left, John Oliver frowns, and goes over to a computer sitting on a table by a bright window with floral drapes. He clicks to a site labeled, in large letters
UPRISING.COM
and the subhead
Saving America's Bakin'
Somewhere below this is a picture showing the exact close-up we were just watching of Oliver's non-rising dough, with the caption "Buns won't rise?" and a big cheery "GET HELP!" button.
On the right, the hands go over to an old DOS computer next to a slightly grimy window. At the blinking prompt they haltingly begin to type. It goes like this, with an audible thud at each Enter.
Awkwardly, with frequent backspacing, the hands type
Both cameras then do focus-pulls out the windows, and we see that there are taco trucks outside on both street corners.
The one on the left is painted in colorful, tie-dye-like swirls, and labeled "Bernie's Tacos For All". Bernie is sitting next to it, in his mittened meme image from the Inauguration. Happy puffs of cooking smoke emerge from a pipe on the top. The truck has a long line of excited looking customers of jubilantly varying ages and races and shapes, all of them masked and properly spaced apart. The first two people in line are a woman in a purple coat wearing Converse sneakers, and a woman in a yellow coat with a red hair-wrap.
The one on the right is painted military-surplus green, and labeled "Rudy's Taco's and Landscaping", with the extra apostrophe. There are no customers. The only sign of life is a tarry black substance slowly dripping from one corner of the truck onto the ground.
Focus pulls inside as John Oliver clicks "GET HELP!" and the hands hit Enter again, and then back outside to the trucks again.
A siren on the top of Bernie's truck starts flashing, triggered by the GET HELP!, and a little plume of glitter spews out of the smoke pipe. A door in the back of the truck opens, and two figures emerge, their details obscured in the shadow of the truck. They start to walk purposefully towards the house, and we thus lose sight of them as they move out of the frame of the window.
Rudy's truck doesn't react. After the figures move out of view on the left we hold on both scenes for a few more moments, and then a black drone carrying a package buzzes over the Rudy's truck towards the hands' door with an ominous, sputtery noise.
Both sides of the screen now cut to front doors from inside.
John Oliver opens his door, and standing there are John Cena and Adam Driver. Both are masked, but shirtless. Cena carries a big bag labeled "Self-Rising Multigrain Flour". Driver carries a package labeled "Vader BratWorst", containing absurdly large sausages.
The hands open their door. There is nobody there. After a pause the camera pans downward, and sitting on the doormat (which, if you can quickly read upside-down, you will realize says "UNWELCOME") is a cookbook titled "Making America Gluten Again".
The left side then shows a dreamy montage of proper bread-making. At one point we see a close-up of Oliver's hands again awkwardly kneading the dough, and then Driver's hands slide in on top of his in an electrifying homage to the Moore/Swayze ceramic scene in Ghost. After a few moments Cena's hands also join. The clock appears again, and the dough rises...emphatically.
The right side shows the hands occasionally poking at the same blob of flour and Diet Coke. The clocks appears here again in sync with the left side, but the blob of course still does not rise or otherwise change.
On the left we see John Oliver putting a large pan of bun-shapes into the oven. While they bake in appetizing time-lapse, the right shows the hands going into the next room. This is completely full of MyPillow boxes, stacked haphazardly, in a wide range of sizes and shapes. The hands push aside a couple of the stacks in the front and from behind them extract a single tiny MyPillow box the shape of a hot-dog bun.
Both sides cut back to the kitchen counters.
John Oliver has a row of six beautiful hot-dog buns, somehow complete with grill lines, neatly spread open. He puts steaming, shiny hot dogs into the first five, and then an outlandishly oversized sausage into the sixth.
The hands fumble with the small MyPillow box, but eventually manage to get it open and take out a single slightly-mushed white-bread bun, which they place down next to the flour/soda sludge. They put one lumpy tofu-pup into it. They angrily shake a ketchup bottle over this, then open and squeeze it. A large blop of red ketchup, speckled with blue and white spots of mold, splats out across the middle of the pup, bits of it getting on the counter and onto the edge of the flour/soda sludge.
On the left, John Oliver is holding two ketchup-shaped bottles. One is labeled "Joy", the other "Relief". He holds them both over the row of hot dogs, and with an elegant two-handed flourish, squeezes them across the row. Through CGI magic, this extrudes a beautiful, perfectly sine-waved, rainbow-striated ribbon of condiments onto each hot-dog. He puts down the bottle and picks up one hot dog in each hand. From out of the frame on one side, Driver's hands come in and take a hot dog each. From the other side, Cena's hands come in and take the last two. Oliver salutes the camera with his left-hand dog as he bites into the right-hand one. He chews with obvious enjoyment.
On the right, the right hand picks up the forlorn tofu pup, raises it slightly, and then falters. The left hand joins, and two-handedly they lift it up past the camera and out of the frame. After a few seconds they put it down again with a small bite taken out of the end. A couple moments later there is a small coughing noise, and very small bit of chewed tofu-pup lands on the counter in between the tofu pup and the flour/soda sludge.
The screens fade to white, the split dissolving. The words
Last Week Tonight
A New Season
appear, centered. Driver, in Vader costume, leaps into view and slashes the "A New Season" line with his light saber, which turns it into a slightly smoking "A New Administration". After he disappears, one of the small chubby hands appears holding a sharpie. It crosses out "Administration" and writes in "SeAsun". The other hand joins it, and together they attempt to break the sharpie in half, but after several ineffectual, obviously-straining attempts, give up, throw it out of view, and themselves retreat.
That is all.
We open on a close-up of a newspaper with the banner headline
INAUGURATION TOMORROW
and the subhead
President-Elect Announces National Socially-Distanced Hot Dog Cookout
The newspaper then doubles and flies into both sides of a split-screen.
On the left side, the person holding it puts it down, and we see that it's John Oliver. He nods and goes the refrigerator and gets out a package of hot dogs. As he puts it on the counter, we see that the brand is "Hebrew Multinational". He rummages around in the fridge looking for buns.
On the right side, the person puts the paper down, but the camera follows the paper in a POV manner, and thus we see only a pair of small but chubby and slightly orange hands. The hands go to the fridge. It is mostly empty, except that the door shelves are completely full of Diet Coke bottles (all of which have been partially drunk to different levels), the bottom shelf has some crumpled Big Mac wrappers, and the vegetable drawer has the discarded lettuce from a few dozen burgers. And on a middle shelf there is a single lonely package labeled "MyPillow Tofu Pups". This is crossed out in sharpie and "TrumP SteAks" is written over it. The hands hesitate for several seconds before drooping resignedly and taking out the tofu pups.
On the left, John Oliver's voice says, delightedly, "I'll make some buns!", and he opens a pantry to get out a bag of white flour, and then a cabinet to get a mixing bowl.
On the right a defeated voice just mutters, limply, "buns...". The hands open a pantry-like door, but there's nothing inside except 3 crusty bottles of unrefrigerated ketchup and a single bag of white flour. (If you look closely, this says "power" on it instead of "flour".)
Both sides then show quick montages of dough-making activities.
John Oliver mixes water into the flour with quick motions of a wooden spoon until it starts to stick together, and then dumps it out on a cutting board and kneads it with earnest but tentative motions.
The hands dump some flour directly on the formica countertop, pour a blurp of Diet Coke on it, and then poke at it desultorily.
John Oliver, reading aloud from a recipe, says "Allow dough to rise." Animated clocks appear in the corners of both sides, the cameras both zoom in on the blobs of dough/flour, and the clocks spin through an hour or two without any visual change in either blob. The clocks disappear and the cameras zoom back out.
On the left, John Oliver frowns, and goes over to a computer sitting on a table by a bright window with floral drapes. He clicks to a site labeled, in large letters
UPRISING.COM
and the subhead
Saving America's Bakin'
Somewhere below this is a picture showing the exact close-up we were just watching of Oliver's non-rising dough, with the caption "Buns won't rise?" and a big cheery "GET HELP!" button.
On the right, the hands go over to an old DOS computer next to a slightly grimy window. At the blinking prompt they haltingly begin to type. It goes like this, with an audible thud at each Enter.
>: TWITTER.COM
**account blocked**
>: UPRISING.COM
**account blocked**
>: QANON.COM
welcome to
Questions
ANONymous
Enter your embarrassing question:
Awkwardly, with frequent backspacing, the hands type
>: FLABBBY BUNS
Both cameras then do focus-pulls out the windows, and we see that there are taco trucks outside on both street corners.
The one on the left is painted in colorful, tie-dye-like swirls, and labeled "Bernie's Tacos For All". Bernie is sitting next to it, in his mittened meme image from the Inauguration. Happy puffs of cooking smoke emerge from a pipe on the top. The truck has a long line of excited looking customers of jubilantly varying ages and races and shapes, all of them masked and properly spaced apart. The first two people in line are a woman in a purple coat wearing Converse sneakers, and a woman in a yellow coat with a red hair-wrap.
The one on the right is painted military-surplus green, and labeled "Rudy's Taco's and Landscaping", with the extra apostrophe. There are no customers. The only sign of life is a tarry black substance slowly dripping from one corner of the truck onto the ground.
Focus pulls inside as John Oliver clicks "GET HELP!" and the hands hit Enter again, and then back outside to the trucks again.
A siren on the top of Bernie's truck starts flashing, triggered by the GET HELP!, and a little plume of glitter spews out of the smoke pipe. A door in the back of the truck opens, and two figures emerge, their details obscured in the shadow of the truck. They start to walk purposefully towards the house, and we thus lose sight of them as they move out of the frame of the window.
Rudy's truck doesn't react. After the figures move out of view on the left we hold on both scenes for a few more moments, and then a black drone carrying a package buzzes over the Rudy's truck towards the hands' door with an ominous, sputtery noise.
Both sides of the screen now cut to front doors from inside.
John Oliver opens his door, and standing there are John Cena and Adam Driver. Both are masked, but shirtless. Cena carries a big bag labeled "Self-Rising Multigrain Flour". Driver carries a package labeled "Vader BratWorst", containing absurdly large sausages.
The hands open their door. There is nobody there. After a pause the camera pans downward, and sitting on the doormat (which, if you can quickly read upside-down, you will realize says "UNWELCOME") is a cookbook titled "Making America Gluten Again".
The left side then shows a dreamy montage of proper bread-making. At one point we see a close-up of Oliver's hands again awkwardly kneading the dough, and then Driver's hands slide in on top of his in an electrifying homage to the Moore/Swayze ceramic scene in Ghost. After a few moments Cena's hands also join. The clock appears again, and the dough rises...emphatically.
The right side shows the hands occasionally poking at the same blob of flour and Diet Coke. The clocks appears here again in sync with the left side, but the blob of course still does not rise or otherwise change.
On the left we see John Oliver putting a large pan of bun-shapes into the oven. While they bake in appetizing time-lapse, the right shows the hands going into the next room. This is completely full of MyPillow boxes, stacked haphazardly, in a wide range of sizes and shapes. The hands push aside a couple of the stacks in the front and from behind them extract a single tiny MyPillow box the shape of a hot-dog bun.
Both sides cut back to the kitchen counters.
John Oliver has a row of six beautiful hot-dog buns, somehow complete with grill lines, neatly spread open. He puts steaming, shiny hot dogs into the first five, and then an outlandishly oversized sausage into the sixth.
The hands fumble with the small MyPillow box, but eventually manage to get it open and take out a single slightly-mushed white-bread bun, which they place down next to the flour/soda sludge. They put one lumpy tofu-pup into it. They angrily shake a ketchup bottle over this, then open and squeeze it. A large blop of red ketchup, speckled with blue and white spots of mold, splats out across the middle of the pup, bits of it getting on the counter and onto the edge of the flour/soda sludge.
On the left, John Oliver is holding two ketchup-shaped bottles. One is labeled "Joy", the other "Relief". He holds them both over the row of hot dogs, and with an elegant two-handed flourish, squeezes them across the row. Through CGI magic, this extrudes a beautiful, perfectly sine-waved, rainbow-striated ribbon of condiments onto each hot-dog. He puts down the bottle and picks up one hot dog in each hand. From out of the frame on one side, Driver's hands come in and take a hot dog each. From the other side, Cena's hands come in and take the last two. Oliver salutes the camera with his left-hand dog as he bites into the right-hand one. He chews with obvious enjoyment.
On the right, the right hand picks up the forlorn tofu pup, raises it slightly, and then falters. The left hand joins, and two-handedly they lift it up past the camera and out of the frame. After a few seconds they put it down again with a small bite taken out of the end. A couple moments later there is a small coughing noise, and very small bit of chewed tofu-pup lands on the counter in between the tofu pup and the flour/soda sludge.
The screens fade to white, the split dissolving. The words
Last Week Tonight
A New Season
appear, centered. Driver, in Vader costume, leaps into view and slashes the "A New Season" line with his light saber, which turns it into a slightly smoking "A New Administration". After he disappears, one of the small chubby hands appears holding a sharpie. It crosses out "Administration" and writes in "SeAsun". The other hand joins it, and together they attempt to break the sharpie in half, but after several ineffectual, obviously-straining attempts, give up, throw it out of view, and themselves retreat.
That is all.
¶ PopCon 2020 · 5 September 2020 listen/tech
The 2020 Pop Conference starts this week! It's online and free, so you can come!
But you do need to register!
My PopCon contribution this year is not a talk, it's a web explorer for the music that defines, unites and distinguishes kids around the world. It's called The Aqueduct of Youth.
It's part of a panel called The Platforms of Youth: Meme-ing, Marketing & Streaming, with five other explorations of "Old Town Road", Christian musicals, aging, Tiktok and VSCO Girls:
You can watch videos from the other participants, drink from the Aqueduct, and then come and ask us questions in our live Zoom discussion session on PopCon's opening day, Wednesday 9/9, from 10:30-11 Pacific / 1:30-2pm Eastern.
But you do need to register!
My PopCon contribution this year is not a talk, it's a web explorer for the music that defines, unites and distinguishes kids around the world. It's called The Aqueduct of Youth.
It's part of a panel called The Platforms of Youth: Meme-ing, Marketing & Streaming, with five other explorations of "Old Town Road", Christian musicals, aging, Tiktok and VSCO Girls:
You can watch videos from the other participants, drink from the Aqueduct, and then come and ask us questions in our live Zoom discussion session on PopCon's opening day, Wednesday 9/9, from 10:30-11 Pacific / 1:30-2pm Eastern.
I grew up in Texas, which is where Juneteenth originated. Either nobody I knew talked about it (and pretty much everybody I knew was white), or they did and I managed to forget. Either one of those is pathetic.
This year is different. This year Juneteenth comes in the middle of a literal viral pandemic and an essential moral revolution to assert the should-be-beyond-obvious truth that Black Lives Matter. I know what the holiday is now, well enough that I could explain it, but you're probably better off letting somebody better qualified than me do that, like Henry Louis Gates, Jr. or Fabiola Cineas or Ben & Jerry.
But I also know what it sounds like, this year, and maybe on this subject I'm actually a qualified reporter. You don't need a gothic-metal/alt-idol fan to tell you about Black protest music from personal experience, but I don't know because I knew, I know because I spent a couple days reading every article I could find about new protest songs, collecting them, and then running a lot of iterative data-analysis over the listening and playlist-making patterns of hundreds of millions of Spotify listeners to find what else the people who know those songs know, and then repeating the process until everything else it gave me was old. I know because people know, and I can find out.
What can you do to hear and amplify Black voices? You can listen. You can turn them up. If you don't have your own place to start, you can start here now.
PS: More new protest songs released on 2020-06-19 itself:
This year is different. This year Juneteenth comes in the middle of a literal viral pandemic and an essential moral revolution to assert the should-be-beyond-obvious truth that Black Lives Matter. I know what the holiday is now, well enough that I could explain it, but you're probably better off letting somebody better qualified than me do that, like Henry Louis Gates, Jr. or Fabiola Cineas or Ben & Jerry.
But I also know what it sounds like, this year, and maybe on this subject I'm actually a qualified reporter. You don't need a gothic-metal/alt-idol fan to tell you about Black protest music from personal experience, but I don't know because I knew, I know because I spent a couple days reading every article I could find about new protest songs, collecting them, and then running a lot of iterative data-analysis over the listening and playlist-making patterns of hundreds of millions of Spotify listeners to find what else the people who know those songs know, and then repeating the process until everything else it gave me was old. I know because people know, and I can find out.
What can you do to hear and amplify Black voices? You can listen. You can turn them up. If you don't have your own place to start, you can start here now.
PS: More new protest songs released on 2020-06-19 itself:
¶ BORGLY: A collaborative global survival game. · 15 March 2020
[Keeping track of isolation, interactions and uncertain status of untested people is going to be complicated and difficult, but necessary to stop the spread of COVID-19. A tracking application would help, but even a simple set of rules would be better than nothing. Here is an attempt to formulate what they would be, in the style of a collaborative game.]
BORGLY: A collaborative global survival game.
Players
Everyone.
Summary
BORGLY is a collaborative global survival game played with colors (Black Orange Red Green Lavender Yellow, thus the name) and numbers. Not only can everybody play, but even people who do not think they are playing are part of the game. It's literally a game for everybody. In this game we are all the Borg. We are all inextricably linked by our actions. And a virus.
The Colors
- Yellow: no symptoms, infection status unknown
- Green: uninfected
- Orange: contact or symptoms but untested
- Red: tested positive
- Lavender: recovered
- Black: dead
Starting the Game
All players begin the game with the color Yellow, and the score 0.
Ending the Game
The game ends when all players are any combination of Green, Black and Lavender at once. The primary goal is to reach this point in the shortest time, with the fewest players at Black. The secondary goal is to reach it with the fewest at Lavender.
Playing the Game
The game is played in real-time. All players are active at all times, there are no turns. You play by isolating and/or failing to isolate.
Isolating
Isolating is defined as:
- not coming within 6 feet of any human who is not either at Green or in your Cluster
- not doing so indirectly by exposure to objects or surfaces
Isolating for 24 hours scores points (see Scoring, below).
Contact
The failure to Isolate is Contact. Contact thus occurs whenever you come within 6 feet of another human, directly or indirectly via objects or surfaces. Any contact with a player at Red or Orange changes your color to Orange, resets your score to 0, and removes you from your cluster. See Clusters for the rules for contact between players at Green and Yellow. Contact between players who are all at Green has no scoring effect. Contact with a player at Lavender has no color or score effect.
Experiencing Symptoms
Any player who experiences virus symptoms, including fever and shortness of breath, has their score reset to 0 and their color to Orange, and the same with all members of their cluster, which is also immediately dissolved.
Testing
Any player at Green or Yellow who undergoes initial COVID-19 testing and tests positive has their score reset to 0 and their color to Red, and all members of their cluster have their scores reset to 0 and their colors to Orange. If a player at Yellow tests negative, their score is reset to 0 and their color to Green. A player at Orange goes to Red if they test positive, and stays at Orange if they test negative. A player at Red who recovers to no longer experience symptoms, and gets retested negative, goes to Lavender.
Death
Any player who dies during the game has their color changed to Black, and is removed from play. This is what we are playing to avoid. Note that this applies to all deaths, whether from COVID-19 itself or not, so people who die because they could not get healthcare from a hospital overwhelmed by COVID-19 patients count.
Clusters
Each player at Green or Yellow has a Cluster of players, which begins as just themselves. Clusters may be of any size, but see Cluster Checks, below, for the significance of cluster size. Any time two or more players contact who are at any combination of Green and Yellow, and not already all in the same cluster, they must choose one of two actions:
- Merge all of their clusters. Merging immediately resets the scores of all cluster members to the lowest score of any of the members who were at Yellow, and all colors to Yellow.
- Remove themselves from all of their clusters, reset their own colors to Yellow and score to 0.
Contact between players at Green, or cluster members, has no effect on scoring.
Cluster Checks
Every 24 hours, all members of a cluster must report their colors and scores to all other members of the cluster, including any merges caused by any members' non-cluster contact (any combination of collective and pairwise methods is allowed, but remember the Contact rules above). If any cluster member fails to report, the cluster is dissolved and all members are reset to Yellow 0. If any of the cluster members report that their scores have been reset by contact, they are removed from the cluster. If any member has had their color changed by symptoms, positive testing or death, all members are changed to Orange 0 and the cluster is dissolved. Members who remain in the cluster at the end of the check score 1 point. Remember that this is a collaborative game, not a competitive one.
Scoring
- Players at Green score 1 point by isolating (and thus staying Green) for 24 hours.
- Players at Yellow can score only through a combination of isolating for 24 hours and Cluster Checks (see above). Those who score 14 points go to Green.
- Players at Orange can score only by isolating for 24 hours without symptoms. Those who score 14 points go to Green.
- Players at Red accumulate points but can only have their color changed by testing.
- Players at Black or Lavender no longer accumulate points.
Replay
If any players reveal, realize or discover contact that was missed during earlier play, all rules are replayed from that point, including cluster merges and removals. Any Cluster Checks for clusters that change during replay must be reperformed.
Strategy
There are three strategies.
- Normal Routine: In this strategy, there is no Isolating, lots of Contact, and thus lots of Lavender and Black. Since these are the colors we are playing to avoid, this is a bad strategy.
- Passively Isolating: In this strategy you don't go to crowded events that have been canceled anyway, and you don't hang out with friends that aren't hanging out with their friends, but otherwise you do whatever is still possible, and don't really pay attention to your contacts or their states. This prolongs the game for everybody who is trying to play, and thus increases the amount of Lavender and Black, and is thus also a bad strategy.
- Isolating for Real: In this strategy, everybody isolates as much as possible, keeps their clusters as small as possible, and monitors their clusters daily. This is the only way to win.
Player Guide
You begin the game at Yellow, with a score of 0.
Yellow (no symptoms, infection status unknown)
- Score 1 point by restricting contact to your cluster for 24 hours and completing a cluster check.
- On non-cluster Green/Yellow contact you must either
- > Merge clusters and reset all cluster members' scores to 0 and colors to Yellow.
- > Remove yourself from your cluster and reset your score to 0.
- Contact with Orange or Red resets your score to 0 and color to Orange, and removes you from your cluster.
- Failing or missing a cluster check resets your score to 0.
- Experiencing Symptoms resets your score to 0 and color to Orange, along with those of all players in your cluster, and the cluster is dissolved.
- A negative test resets your score to 0 and changes your color to Green.
- A positive test resets your score to 0 and color to Red, along with those of all players in your cluster, and the cluster is dissolved.
- Dying (for any reason) changes your color to Black.
- Scoring 14 points resets your score to 0 and your color to Green, and dissolves your cluster.
Green (uninfected)
- Score 1 point by isolating for 24 hours. There's no inherent value to this in the current edition of the game, but future editions might require more than 14 points to reach Green.
- On Yellow contact you must join the cluster of the player at Yellow, and set your score to theirs.
- Contact with Orange or Red resets your score to 0 and color to Orange.
- Experiencing Symptoms resets your score to 0 and color to Orange.
- A positive test resets your score to 0 and changes your color to Red.
- Dying (for any reason) changes your color to Black.
Orange (contact or symptoms but untested)
- You can't score points or change colors as long as you have symptoms, so all you can do is isolate in order to not turn anybody else to Orange.
- Score 1 point by isolating for 24 hours without symptoms.
- A positive test resets your score to 0 and changes your color to Red.
- If you have no symptoms, a negative test resets your score to 0 and changes your color to Green.
- If you have symptoms, a negative test does not change your color. You're still sick with something.
- Dying (for any reason) changes your color to Black.
- Scoring 14 points resets your score to 0 and your color to Green.
Red (tested positive)
- Score 1 point by isolating for 24 hours.
- Recovering and testing negative changes your color to Lavender.
- Dying changes your color to Black.
Lavender (recovered)
- No personal actions to take, but you may help and advise other players.
Black (dead)
- No personal actions to take.
BORGLY: A collaborative global survival game.
Players
Everyone.
Summary
BORGLY is a collaborative global survival game played with colors (Black Orange Red Green Lavender Yellow, thus the name) and numbers. Not only can everybody play, but even people who do not think they are playing are part of the game. It's literally a game for everybody. In this game we are all the Borg. We are all inextricably linked by our actions. And a virus.
The Colors
- Yellow: no symptoms, infection status unknown
- Green: uninfected
- Orange: contact or symptoms but untested
- Red: tested positive
- Lavender: recovered
- Black: dead
Starting the Game
All players begin the game with the color Yellow, and the score 0.
Ending the Game
The game ends when all players are any combination of Green, Black and Lavender at once. The primary goal is to reach this point in the shortest time, with the fewest players at Black. The secondary goal is to reach it with the fewest at Lavender.
Playing the Game
The game is played in real-time. All players are active at all times, there are no turns. You play by isolating and/or failing to isolate.
Isolating
Isolating is defined as:
- not coming within 6 feet of any human who is not either at Green or in your Cluster
- not doing so indirectly by exposure to objects or surfaces
Isolating for 24 hours scores points (see Scoring, below).
Contact
The failure to Isolate is Contact. Contact thus occurs whenever you come within 6 feet of another human, directly or indirectly via objects or surfaces. Any contact with a player at Red or Orange changes your color to Orange, resets your score to 0, and removes you from your cluster. See Clusters for the rules for contact between players at Green and Yellow. Contact between players who are all at Green has no scoring effect. Contact with a player at Lavender has no color or score effect.
Experiencing Symptoms
Any player who experiences virus symptoms, including fever and shortness of breath, has their score reset to 0 and their color to Orange, and the same with all members of their cluster, which is also immediately dissolved.
Testing
Any player at Green or Yellow who undergoes initial COVID-19 testing and tests positive has their score reset to 0 and their color to Red, and all members of their cluster have their scores reset to 0 and their colors to Orange. If a player at Yellow tests negative, their score is reset to 0 and their color to Green. A player at Orange goes to Red if they test positive, and stays at Orange if they test negative. A player at Red who recovers to no longer experience symptoms, and gets retested negative, goes to Lavender.
Death
Any player who dies during the game has their color changed to Black, and is removed from play. This is what we are playing to avoid. Note that this applies to all deaths, whether from COVID-19 itself or not, so people who die because they could not get healthcare from a hospital overwhelmed by COVID-19 patients count.
Clusters
Each player at Green or Yellow has a Cluster of players, which begins as just themselves. Clusters may be of any size, but see Cluster Checks, below, for the significance of cluster size. Any time two or more players contact who are at any combination of Green and Yellow, and not already all in the same cluster, they must choose one of two actions:
- Merge all of their clusters. Merging immediately resets the scores of all cluster members to the lowest score of any of the members who were at Yellow, and all colors to Yellow.
- Remove themselves from all of their clusters, reset their own colors to Yellow and score to 0.
Contact between players at Green, or cluster members, has no effect on scoring.
Cluster Checks
Every 24 hours, all members of a cluster must report their colors and scores to all other members of the cluster, including any merges caused by any members' non-cluster contact (any combination of collective and pairwise methods is allowed, but remember the Contact rules above). If any cluster member fails to report, the cluster is dissolved and all members are reset to Yellow 0. If any of the cluster members report that their scores have been reset by contact, they are removed from the cluster. If any member has had their color changed by symptoms, positive testing or death, all members are changed to Orange 0 and the cluster is dissolved. Members who remain in the cluster at the end of the check score 1 point. Remember that this is a collaborative game, not a competitive one.
Scoring
- Players at Green score 1 point by isolating (and thus staying Green) for 24 hours.
- Players at Yellow can score only through a combination of isolating for 24 hours and Cluster Checks (see above). Those who score 14 points go to Green.
- Players at Orange can score only by isolating for 24 hours without symptoms. Those who score 14 points go to Green.
- Players at Red accumulate points but can only have their color changed by testing.
- Players at Black or Lavender no longer accumulate points.
Replay
If any players reveal, realize or discover contact that was missed during earlier play, all rules are replayed from that point, including cluster merges and removals. Any Cluster Checks for clusters that change during replay must be reperformed.
Strategy
There are three strategies.
- Normal Routine: In this strategy, there is no Isolating, lots of Contact, and thus lots of Lavender and Black. Since these are the colors we are playing to avoid, this is a bad strategy.
- Passively Isolating: In this strategy you don't go to crowded events that have been canceled anyway, and you don't hang out with friends that aren't hanging out with their friends, but otherwise you do whatever is still possible, and don't really pay attention to your contacts or their states. This prolongs the game for everybody who is trying to play, and thus increases the amount of Lavender and Black, and is thus also a bad strategy.
- Isolating for Real: In this strategy, everybody isolates as much as possible, keeps their clusters as small as possible, and monitors their clusters daily. This is the only way to win.
Player Guide
You begin the game at Yellow, with a score of 0.
Yellow (no symptoms, infection status unknown)
- Score 1 point by restricting contact to your cluster for 24 hours and completing a cluster check.
- On non-cluster Green/Yellow contact you must either
- > Merge clusters and reset all cluster members' scores to 0 and colors to Yellow.
- > Remove yourself from your cluster and reset your score to 0.
- Contact with Orange or Red resets your score to 0 and color to Orange, and removes you from your cluster.
- Failing or missing a cluster check resets your score to 0.
- Experiencing Symptoms resets your score to 0 and color to Orange, along with those of all players in your cluster, and the cluster is dissolved.
- A negative test resets your score to 0 and changes your color to Green.
- A positive test resets your score to 0 and color to Red, along with those of all players in your cluster, and the cluster is dissolved.
- Dying (for any reason) changes your color to Black.
- Scoring 14 points resets your score to 0 and your color to Green, and dissolves your cluster.
Green (uninfected)
- Score 1 point by isolating for 24 hours. There's no inherent value to this in the current edition of the game, but future editions might require more than 14 points to reach Green.
- On Yellow contact you must join the cluster of the player at Yellow, and set your score to theirs.
- Contact with Orange or Red resets your score to 0 and color to Orange.
- Experiencing Symptoms resets your score to 0 and color to Orange.
- A positive test resets your score to 0 and changes your color to Red.
- Dying (for any reason) changes your color to Black.
Orange (contact or symptoms but untested)
- You can't score points or change colors as long as you have symptoms, so all you can do is isolate in order to not turn anybody else to Orange.
- Score 1 point by isolating for 24 hours without symptoms.
- A positive test resets your score to 0 and changes your color to Red.
- If you have no symptoms, a negative test resets your score to 0 and changes your color to Green.
- If you have symptoms, a negative test does not change your color. You're still sick with something.
- Dying (for any reason) changes your color to Black.
- Scoring 14 points resets your score to 0 and your color to Green.
Red (tested positive)
- Score 1 point by isolating for 24 hours.
- Recovering and testing negative changes your color to Lavender.
- Dying changes your color to Black.
Lavender (recovered)
- No personal actions to take, but you may help and advise other players.
Black (dead)
- No personal actions to take.
¶ 2019 in Music · 6 January 2020 essay/listen/tech
I starting making one music-list a year some time in the 80s, before I really knew enough for there to be any sense to this activity. For a while in the 90s and 00s I got more serious about it, and statistically way better-informed, but there's actually no amount of informedness that transforms a single person's opinions about music into anything that inherently matters to anybody other than people (if any) who happen to share their specific tastes, or extraordinarily patient and maybe slightly creepy friends.
Collect people together, though, and the patterns of their love are sometimes very interesting. For several years I presided computationally over an assembly of nominal expertise, trying to find ways to turn hundreds of opinions into at least plural insights. Hundreds of people is not a lot, though, and asking people to pretend their opinions matter is a dubious way to find out what they really love. I'm not really sad we stopped doing that.
Hundreds of millions of people isn't that much, yet, but it's getting there, and asking people to spend their lives loving all the innumerable things they love is a more realistic proposition than getting them to make short numbered lists on annual deadlines. Finding an individual person who shares your exact taste, in the real world, is not only laborious to the point of preventative difficulty, but maybe not even reliably possible in theory. Finding groups of people in the virtual world who collectively approximate aspects of your taste is, due to the primitive current state of data-transparency, no easier for you.
But it has been my job, for the last few years, to try to figure out algorithmic ways to turn collective love and listening patterns into music insights and experiences. I work at Spotify, so I have extremely good information about what people like in Sweden and Norway, fairly decent information about most of the rest of Europe, the Americas and parts of Asia, and at least glimmers of insight about literally almost everywhere else on Earth. I don't know that much about you, but I know a little bit about a lot of people.
So now I make a lot of lists. Here, in fact, are algorithmically-generated playlists of the songs that defined, united and distinguished the fans and love and new music in 2000+ genres and countries around the world in 2019:
2019 Around the World
You probably don't share my tastes, and this is a pretty weak unifying force for everybody who isn't me, but there are so many stronger ones. Maybe some of the ones that pull on you are represented here. Maybe some of the communities implied and channeled here have been unknowingly incomplete without you. Maybe you have not yet discovered half of the things you will eventually adore. Maybe this is how you find them.
I found a lot of things this year, myself, some of them in this process of trying to find music for other people, and some of them just by listening. You needn't care about what I like. And if for some reason you do, you can already find out what it is in unmanageable weekly detail. But I like to look back at my own years. Spotify's official forms of nostalgia so far define years purely by listening dates, but as a music geek of a particular sort, what I mean by a year is music that was both made and heard then. New music.
I no longer want to make this list by applying manual reductive retroactive impressions to what I remember of the year, but I also don't have to. Adapting my collective engines to the individual, then, here is the purely data-generated playlist of the new music to which I demonstrated the most actual listening attachment in 2019:
2019 Greatest Hits (for glenn mcdonald)
And for segmented nostalgia, because that's what kind of nostalgist I am, I also used genre metadata and a very small amount of manual tweaking to almost automatically produce three more specialized lists:
Bright Swords in the Void (Metal and metal-adjacent noises, from the floridly melodic to the stochastically apocalyptic.)
Gradient Dissent (Ambient, noise, epicore and other abstract geometries.)
Dancing With Tears (Pop, rock, hip hop and other sentimental forms.)
And finally, although surely this, if anything, will be of interest to absolutely nobody but me, I also used a combination of my own listening, broken down by genre, and the global 2019 genre lists, to produce a list of the songs I missed or intentionally avoided despite their being popular with the fans of my favorite genres.
2019 Greatest Misses (for glenn mcdonald)
I made versions of this Misses list in November and December, to see what I was in danger of missing before the year actually ended, so these songs are the reverse-evolutionary survivors of two generations of augmented remedial listening. But I played it again just now, and it still sounds basically great to me. I'm pretty sure I could spend the next year listening to nothing but songs I missed in 2019 despite trying to hear them all, and it would be just as great in sonic terms. There's something hypothetically comforting in that, at least until I starting trying to figure out what kind of global catastrophe I'm effectively imagining here. I'm alive, but all the musicians in the world are dead? Or there's no surviving technology for recording music, but somehow Spotify servers and the worldwide cell and wifi networks still work?
Easier to live. I now declare 2019 complete and archived. Onwards.
Collect people together, though, and the patterns of their love are sometimes very interesting. For several years I presided computationally over an assembly of nominal expertise, trying to find ways to turn hundreds of opinions into at least plural insights. Hundreds of people is not a lot, though, and asking people to pretend their opinions matter is a dubious way to find out what they really love. I'm not really sad we stopped doing that.
Hundreds of millions of people isn't that much, yet, but it's getting there, and asking people to spend their lives loving all the innumerable things they love is a more realistic proposition than getting them to make short numbered lists on annual deadlines. Finding an individual person who shares your exact taste, in the real world, is not only laborious to the point of preventative difficulty, but maybe not even reliably possible in theory. Finding groups of people in the virtual world who collectively approximate aspects of your taste is, due to the primitive current state of data-transparency, no easier for you.
But it has been my job, for the last few years, to try to figure out algorithmic ways to turn collective love and listening patterns into music insights and experiences. I work at Spotify, so I have extremely good information about what people like in Sweden and Norway, fairly decent information about most of the rest of Europe, the Americas and parts of Asia, and at least glimmers of insight about literally almost everywhere else on Earth. I don't know that much about you, but I know a little bit about a lot of people.
So now I make a lot of lists. Here, in fact, are algorithmically-generated playlists of the songs that defined, united and distinguished the fans and love and new music in 2000+ genres and countries around the world in 2019:
2019 Around the World
You probably don't share my tastes, and this is a pretty weak unifying force for everybody who isn't me, but there are so many stronger ones. Maybe some of the ones that pull on you are represented here. Maybe some of the communities implied and channeled here have been unknowingly incomplete without you. Maybe you have not yet discovered half of the things you will eventually adore. Maybe this is how you find them.
I found a lot of things this year, myself, some of them in this process of trying to find music for other people, and some of them just by listening. You needn't care about what I like. And if for some reason you do, you can already find out what it is in unmanageable weekly detail. But I like to look back at my own years. Spotify's official forms of nostalgia so far define years purely by listening dates, but as a music geek of a particular sort, what I mean by a year is music that was both made and heard then. New music.
I no longer want to make this list by applying manual reductive retroactive impressions to what I remember of the year, but I also don't have to. Adapting my collective engines to the individual, then, here is the purely data-generated playlist of the new music to which I demonstrated the most actual listening attachment in 2019:
2019 Greatest Hits (for glenn mcdonald)
And for segmented nostalgia, because that's what kind of nostalgist I am, I also used genre metadata and a very small amount of manual tweaking to almost automatically produce three more specialized lists:
Bright Swords in the Void (Metal and metal-adjacent noises, from the floridly melodic to the stochastically apocalyptic.)
Gradient Dissent (Ambient, noise, epicore and other abstract geometries.)
Dancing With Tears (Pop, rock, hip hop and other sentimental forms.)
And finally, although surely this, if anything, will be of interest to absolutely nobody but me, I also used a combination of my own listening, broken down by genre, and the global 2019 genre lists, to produce a list of the songs I missed or intentionally avoided despite their being popular with the fans of my favorite genres.
2019 Greatest Misses (for glenn mcdonald)
I made versions of this Misses list in November and December, to see what I was in danger of missing before the year actually ended, so these songs are the reverse-evolutionary survivors of two generations of augmented remedial listening. But I played it again just now, and it still sounds basically great to me. I'm pretty sure I could spend the next year listening to nothing but songs I missed in 2019 despite trying to hear them all, and it would be just as great in sonic terms. There's something hypothetically comforting in that, at least until I starting trying to figure out what kind of global catastrophe I'm effectively imagining here. I'm alive, but all the musicians in the world are dead? Or there's no surviving technology for recording music, but somehow Spotify servers and the worldwide cell and wifi networks still work?
Easier to live. I now declare 2019 complete and archived. Onwards.
¶ Hyperspace House Concerts · 26 October 2018 listen/tech
One of the questions we've yet to exactly answer, about the new streaming-based music business, is how you get started in it. In the old business, you mostly got started by playing your music for people near you. The new one has the potential to be strictly better than this, it seems to me, both by giving you more power to reach the people around you even when you aren't on a stage in one of their bars, and by giving listeners the ability to effectively warp to your town to hear you without leaving theirs.
For locally-popular artists seeking even-wider audiences, at least, Every Place at Once is an experimental partial answer: an algorithmic semi-global explorer of the music distinctively popular in individual cities. That relies on a fair amount of listening signal to operate, though, and thus doesn't really answer the question about getting started. How do you get to be locally popular? How do you move from you playing your songs for friends to strangers listening to your songs of their own accord?
I had been mostly ignoring this problem, having tried pushing the thresholds of Every Place at Once lower with results that were more worse than better, but periodically some new potential computational approach occurs to me. And usually also doesn't work. But this week, actually, one of these failed to fail as conclusively. It turns out that even at very low listening levels (on the order of tens of listeners, not even hundreds), if most of a song's listeners are in a single place, there's a pretty good chance that there's a reason for that. And, usefully, "That's where the band is from" turns out to be the most common one.
So I made another thing. If artists with tens of fans are the scale where you might play house concerts, this thing is an attempt at algorithmic semi-global Hyperspace House Concerts.
You can see pretty quickly that it's at least sometimes working: if you're listening to Harvard or MIT a cappella groups, you're probably in Cambridge. Mjangles is a rapper born in Ghana and raised in the Bronx, but he's currently a sophomore at Harvard. And even the music that isn't from Cambridge sometimes turns out to have interesting local stories. Jocelyn Hagen is a choral composer from North Dakota, but the week the list above was generated, her piece "Moon Goddess" was being rehearsed by a Harvard choir for an imminent concert. I didn't find as clear an explanation for André Caplet's similarly-lovely choral piece, but it was once performed by the Radcliffe Choral Society, so perhaps it still lingers in the walls.
And if some of this signal turns out to be noise, maybe that's OK. Sometimes the music in a place is coming out of the open windows of a passing car. And if 10 cars pass you blasting the same song, now it's part of your city.
So poke around, listen, see what you can find. Start where you live, and then try some places where you don't. There are lists for 500+ cities around the world, automatically updated every week, and more will appear as listening allows. And your listening can be part of it, part of how music travels and how careers begin and how we all find out what we're like.
For locally-popular artists seeking even-wider audiences, at least, Every Place at Once is an experimental partial answer: an algorithmic semi-global explorer of the music distinctively popular in individual cities. That relies on a fair amount of listening signal to operate, though, and thus doesn't really answer the question about getting started. How do you get to be locally popular? How do you move from you playing your songs for friends to strangers listening to your songs of their own accord?
I had been mostly ignoring this problem, having tried pushing the thresholds of Every Place at Once lower with results that were more worse than better, but periodically some new potential computational approach occurs to me. And usually also doesn't work. But this week, actually, one of these failed to fail as conclusively. It turns out that even at very low listening levels (on the order of tens of listeners, not even hundreds), if most of a song's listeners are in a single place, there's a pretty good chance that there's a reason for that. And, usefully, "That's where the band is from" turns out to be the most common one.
So I made another thing. If artists with tens of fans are the scale where you might play house concerts, this thing is an attempt at algorithmic semi-global Hyperspace House Concerts.
You can see pretty quickly that it's at least sometimes working: if you're listening to Harvard or MIT a cappella groups, you're probably in Cambridge. Mjangles is a rapper born in Ghana and raised in the Bronx, but he's currently a sophomore at Harvard. And even the music that isn't from Cambridge sometimes turns out to have interesting local stories. Jocelyn Hagen is a choral composer from North Dakota, but the week the list above was generated, her piece "Moon Goddess" was being rehearsed by a Harvard choir for an imminent concert. I didn't find as clear an explanation for André Caplet's similarly-lovely choral piece, but it was once performed by the Radcliffe Choral Society, so perhaps it still lingers in the walls.
And if some of this signal turns out to be noise, maybe that's OK. Sometimes the music in a place is coming out of the open windows of a passing car. And if 10 cars pass you blasting the same song, now it's part of your city.
So poke around, listen, see what you can find. Start where you live, and then try some places where you don't. There are lists for 500+ cities around the world, automatically updated every week, and more will appear as listening allows. And your listening can be part of it, part of how music travels and how careers begin and how we all find out what we're like.
¶ Music Demographics, Accountability and Short Blasts of Finnish Metal · 27 April 2018 listen/tech
On 27 April 2018 I gave a talk at the 2018 Pop Conference called "Panic, Death and Other Gender Patterns in Spotify Listening".
The talk itself involved enough snapshots of changing data and short blasts of music that I am not going to attempt to transpose it directly to blog form, but the main point of it was to introduce some new things I have added to everynoise.com having to do with music and gender and numbers and genres and accountability and hope.
Demographics and Listening
The first of these things is an interactive index to the distinctive musical tastes of Spotify listeners divided by country/age/gender demographic groups. It is here:
Every Demographic at Once
This is similar in structure to Every Place at Once, which explores listening by city, and I retrofitted some new features from the demographic version to the geographic one, so both now try to describe each group's tastes in both genre and song terms.
The demographic groups include, where data allows, country/age groups who self-identify as nonbinary, which Spotify began offering as a gender choice in September 2016.
There's even a playlist of the music most distinctively popular among nonbinary listeners as a global group, which I played some songs from in the talk, and which you can hear here:
Streamshare
The second thing I discussed is an automatically-updating dataview breaking down the current share of Spotify streams in each country by artist-gender. That's here:
Female-Artist Streamshare by Country
It has data for each country overall, but also separately for "direct" listening (people going directly to album or artist pages and explicitly playing something), for Spotify's algorithmic personalized Discover Weekly playlists, and for Spotify's featured editorial playlists.
The initial state of this data was about like this:
- Per-country female-artist streamshare, by the most optimistic definition of "female artist" I could construct from my existing data, which is "music whose performers are not exclusively male", varies from about 16-33%.
- You might hope, or even expect, that listeners might seek out more female artists on their own than when they are just listening to other people's playlists or editorial programming, but in fact it's currently the reverse, and female streamshare of direct listening is consistently lower.
- Discover Weekly has notably lower female-artist streamshare than overall or direct listening. This is not very surprising, because DW is powered by co-reference in Spotify playlists, and globally male listeners make more and longer playlists than female listeners on average, so this is a pretty textbook example of algorithmic confirmation bias due to inherent asymmetries in the data inputs.
- Spotify editorial programming, on the other hand, actually has a significantly higher percentage of female-artist streams in general and in almost every country. (Which is an intentional state brought about and maintained by specific Spotify editorial effort.)
Genre Patterns
The third thing is a similar automatically-updating dataview of genres and their shares of both female listeners and streams from female or mixed-gender artists.
Gender Listening Patterns by Genre
There is a wide array of interesting individual differences across the genre spectrum, but the discouragingly unsurprising overall insight is that male listeners stream less from female artists than female listeners do, and in general even female listeners don't stream equally.
In an attempt to see what I could do to push against these inclinations, I took this genre and gender data and produced an experimental set of playlists that try to collect music by female or mixed-gender artists in every individual specific microgenre. The "genre" column in this table links to these, and initially about 1000 genres had enough artist-gender and genre-listening data to support playlists.
Obviously this is not the first time anybody has tried to make female-artist genre playlists, but to me these efforts too often use only a very reductive high-level notion of genre, like "Women in Pop" and "Women in Rock", and thus seem inherently tokenistic. This also tends to implicitly characterize the presence of women in music as a novelty and a separate subject from music itself. The converse ideal, I think, is for it to be true and well-understood that there are women making every kind of music, and for it to be possible to find and listen to filtered subsets of genre music by female or mixed-gender artists without this seeming token or novel. At best these lists would be amazing just because music made by humans is consistently and profoundly amazing.
In many genres, as you can trivially discover by exploring these lists, we are nowhere near this gender-balanced ideal. In some cases my robots couldn't find any plausible intersections between genre and gender at all, and in some of the playlists they did generate, the artists may be "mixed gender" on dubious technicalities, or the music may be more culturally adjacent to the genre than in it.
But the good news about this set of battles in the fight to undo the miserable legacies of chauvinism and patriarchy is that at worst you'll hear some additional music by men, which is sometime surprisingly decent, or you'll end up listening to some music that isn't exactly what you asked for, which is also not a terrible idea for life.
[The playlist I used for example snippets during the talk will make very little explanatory sense on its own, but it has music, and so I include it here for posterity, in case posterity runs out of music of its own.]
[5 June 2018: For anybody who wants a concise tl;dr instead of these detailed breakdowns, I added a summary.]
The talk itself involved enough snapshots of changing data and short blasts of music that I am not going to attempt to transpose it directly to blog form, but the main point of it was to introduce some new things I have added to everynoise.com having to do with music and gender and numbers and genres and accountability and hope.
Demographics and Listening
The first of these things is an interactive index to the distinctive musical tastes of Spotify listeners divided by country/age/gender demographic groups. It is here:
Every Demographic at Once
This is similar in structure to Every Place at Once, which explores listening by city, and I retrofitted some new features from the demographic version to the geographic one, so both now try to describe each group's tastes in both genre and song terms.
The demographic groups include, where data allows, country/age groups who self-identify as nonbinary, which Spotify began offering as a gender choice in September 2016.
There's even a playlist of the music most distinctively popular among nonbinary listeners as a global group, which I played some songs from in the talk, and which you can hear here:
Streamshare
The second thing I discussed is an automatically-updating dataview breaking down the current share of Spotify streams in each country by artist-gender. That's here:
Female-Artist Streamshare by Country
It has data for each country overall, but also separately for "direct" listening (people going directly to album or artist pages and explicitly playing something), for Spotify's algorithmic personalized Discover Weekly playlists, and for Spotify's featured editorial playlists.
The initial state of this data was about like this:
- Per-country female-artist streamshare, by the most optimistic definition of "female artist" I could construct from my existing data, which is "music whose performers are not exclusively male", varies from about 16-33%.
- You might hope, or even expect, that listeners might seek out more female artists on their own than when they are just listening to other people's playlists or editorial programming, but in fact it's currently the reverse, and female streamshare of direct listening is consistently lower.
- Discover Weekly has notably lower female-artist streamshare than overall or direct listening. This is not very surprising, because DW is powered by co-reference in Spotify playlists, and globally male listeners make more and longer playlists than female listeners on average, so this is a pretty textbook example of algorithmic confirmation bias due to inherent asymmetries in the data inputs.
- Spotify editorial programming, on the other hand, actually has a significantly higher percentage of female-artist streams in general and in almost every country. (Which is an intentional state brought about and maintained by specific Spotify editorial effort.)
Genre Patterns
The third thing is a similar automatically-updating dataview of genres and their shares of both female listeners and streams from female or mixed-gender artists.
Gender Listening Patterns by Genre
There is a wide array of interesting individual differences across the genre spectrum, but the discouragingly unsurprising overall insight is that male listeners stream less from female artists than female listeners do, and in general even female listeners don't stream equally.
In an attempt to see what I could do to push against these inclinations, I took this genre and gender data and produced an experimental set of playlists that try to collect music by female or mixed-gender artists in every individual specific microgenre. The "genre" column in this table links to these, and initially about 1000 genres had enough artist-gender and genre-listening data to support playlists.
Obviously this is not the first time anybody has tried to make female-artist genre playlists, but to me these efforts too often use only a very reductive high-level notion of genre, like "Women in Pop" and "Women in Rock", and thus seem inherently tokenistic. This also tends to implicitly characterize the presence of women in music as a novelty and a separate subject from music itself. The converse ideal, I think, is for it to be true and well-understood that there are women making every kind of music, and for it to be possible to find and listen to filtered subsets of genre music by female or mixed-gender artists without this seeming token or novel. At best these lists would be amazing just because music made by humans is consistently and profoundly amazing.
In many genres, as you can trivially discover by exploring these lists, we are nowhere near this gender-balanced ideal. In some cases my robots couldn't find any plausible intersections between genre and gender at all, and in some of the playlists they did generate, the artists may be "mixed gender" on dubious technicalities, or the music may be more culturally adjacent to the genre than in it.
But the good news about this set of battles in the fight to undo the miserable legacies of chauvinism and patriarchy is that at worst you'll hear some additional music by men, which is sometime surprisingly decent, or you'll end up listening to some music that isn't exactly what you asked for, which is also not a terrible idea for life.
[The playlist I used for example snippets during the talk will make very little explanatory sense on its own, but it has music, and so I include it here for posterity, in case posterity runs out of music of its own.]
[5 June 2018: For anybody who wants a concise tl;dr instead of these detailed breakdowns, I added a summary.]