furia furialog · Every Noise at Once · New Particles · The War Against Silence · Aedliga (songs) · photography · other things · contact
17 December 2023 to 5 September 2020
I did my job with love and belief. This was always obviously risky. I had no illusions that the love was returned, or that it is even possible for a public corporation of non-trivial scale to behave in human ways at all.  

It's easy to find cogent advice for how to modulate your emotional attachment to your job, so that losing it is not like losing a part of yourself. I cheerfully recommend ignoring this. The world is better if everybody does their jobs with love and commitment. You definitely want everybody who does a job that affects you to do it with love, so lead by example. This method will result in sporadic stabs of excruciating pain, but the parts of you you lose to jobs regrow quickly, even if you sometimes have to rub some numbing ointment on the wounds for a while.  

The advice industry, like most modern industries, encodes a sneaky bias to sustain corporatism by implicitly casting individual adaptation as the only medium for change. Good luck finding books that somberly advise corporations on how to encourage a dangerous reliance on unsupervised individual inspiration. I have to get a new job now, or something of the sort, but that's only one small problem to solve. The company I no longer work at has to sort through a thousand things I used to do, almost all of which I did because I thought they ought to get done, and then other people came to depend on them because I was right. A large company would probably never hire someone into a role with this little structure, but the startup where I began was inherently based on the individual efforts of its founders and other early employees, and once we were acquired I just kept doing the job my way and it took 10 years for somebody to stop me.  

This is problematic, clearly. A company needs to be able to treat its employees as interchangeable and expendable, both individually and collectively. It needs to be able to periodically layoff 17% of its workforce to cut its margin overhead by 1% and temporarily boost its stock price by 5%, without having to endure existential upheaval to its ongoing business processes. It needs to be able to double and redouble recklessly in size for the same dubious market reasons, without those people all piling up in the lobby where their chaos is visible from the street. Both expansions and contractions are actions of corporate musculature, flexed as much for show as for motive.  

The key to these flexibilities, as we have understood at least since Henry Ford, is to formalize the operational roles so that their function in the overall system is symbolic and anonymous. As long as people are just units inserted into well-defined slots, the machinery doesn't need to care who they are.  

But the resulting machine, because it operates symbolically on abstract definitions, cannot readily adapt. It needs to "innovate", we know, but if you bring a new idea to a well-organized unit in a corporate machine, it will efficiently reroute you into a well-defined pipeline for queuing up potential future input for consideration two quarters from now, because the defining quality of a well-organized unit in a well-organized organization is that it already has its next six months of work fully prioritized in alignment with established corporate goals.  

Whereas if you came to me with a new idea, or an unanswered question whose answer might suggest new ideas, or a problem that might be solved by something I already figured out, I would listen to you, and ask some questions, and gradually pivot my body towards my keyboard as we talked until eventually I started typing. Sometimes, after a minute of this, I would say "Sorry, I'm still listening, but give me five minutes and let me see what I can figure out." Occasionally I'd have to say "This is interesting, but it's kind of complicated. Can I poke at it a bit and get back to you tomorrow?" I could do new things because my inquiries weren't prescribed. I was prepared to solve unexpected problems because I spent most of my time unexpecting things and seeing where that took me.  

There are, of course, books about corporate agility. There are ways to keep the latency for change to smaller increments than quarters or even months. But none of them advise you to find individual people who happen to be able to do pertinent unique work on the fly, just because they have the right combination of skills and knowledge and stubbornness. You can't sell a book of methodology in which a crucial step is "Luck into anomalous contributors". Anomalies are exactly what prudent processes attempt to preclude.  

But everybody is better off if companies ignore this caution with the same exuberant disregard as people doing their jobs with inadvisable devotion. The most transformational human ideas begin in individual hearts, whatever gantlets of brainstorming and strategic opportunity-analysis they subsequently have to run. Spotify was more right, I think, to tolerate my curiosities and experiments for 10 years than they were to finally give up on them out of exasperation or ignorance. Spotify, like probably every other interesting company, only exists because a few people once had unruly unsupervised impulses that the better-organized status quo couldn't accommodate. The secret truth of business advice is that it's mostly about how to grimly extract residual value from the luck you already had, and the unearned love you were already unguardedly given, because there's really no method for making more of it.
There were a lot of things on Every Noise at Once that updated daily or weekly, and some of them will lose value only slowly now that they can't be updated. The one that loses almost all of its value at once is the weekly New Releases by Genre.  

There were no new-release features in Every Noise at Once at its literal outset, pre-Spotify when it was powered by second-hand Echo Nest data and the Rdio API. I found a 2014-07-30 message from me on I Love Music sharing the URL of the first single-page version of a Spotify new-release list, but the earliest capture in the Internet Archive is from 2014-09-24, when Maroon 5's "Maps" was the top single of the week, and the righthand column listed "all 3304 releases this week". I called this version the Spotify Sorting Hat, because certain things hadn't happened yet.  

By 2019 that version became untenable, and I rewrote it from scratch to separate the genre collation from the raw list, and introduce more control so you had a prayer of finding the subset of music you actually cared about. That version is dead now without the internal Spotify feeds that provided its data.  

You might imagine that there would be alternatives by now, but there aren't any on the same scale. Spotify has by far the best API for this kind of idea, but it isn't quite set up to provide any of the three things that a serious new-release tool should offer:  

- "all" new releases: in truth I started imposing thresholds on what the Sorting Hat would include before switching to NRbG, and NRbG never showed literally everything, either. But it showed a lot. The Spotify API for searching allows you to specify "tag:new" and get only things released in the last two weeks, but you can only get 50 of them at a time, and only 1000 total, sorted by popularity. Most weeks there are more than 100,000.  

- new releases by genre: you can filter by genre in the Spotify API, but only in artist searches. And you can only use "tag:new" in album searches. So currently they can't be combined. Unlike the all-release issue, this one would be a reasonable feature request for the API, as it fits the existing usage-models and wouldn't be particularly onerous to support. Assigning artist-level genres to albums can get existential if you think too hard about it, but if you stick to the idea that genres are communities, then calling an album "atmospheric black metal" is shorthand for saying that it's an album made by a band that is part of the atmospheric black metal community, which makes sense even if the particular album is acoustic folk pastiches, and in the new-release case gets it to the audience that wants to know about that album, so it's fine.  

- discovery: the more complicated thing NRbG did was to try to distribute new releases by bands who aren't really the canonical representatives of any genre to the genres whose fans would be their most likely audiences. This absolutely can't be done using the existing API, for the same reasons that you can't extract a "full" list. You can get the 20 most similar artists for any artist, but for matching unknown artists to genres you need to go in the other direction, finding the 100s of artists whose Fans Also Like lists includes the known artists in a genre. But adding this feature to the API wouldn't be much harder than adding the genre filter itself.  

Absent those features, the Spotify API can't be used to build this, and so far all the other services are even farther from being able to provide the tools for it. NRbG worked because the end results weren't confidential, just inaccessible, and I could solve the inaccessibility by running a set of carefully interlocking internal queries. Now I can't.  

I don't really know how we can do new-release discovery now, without this. We can go back to the human, community-based modes of knowledge we used to use, of course: mailing lists, discussion forums, blogs, playlists maintained by individual experts. One genre at a time, these ways are usually better than queries, detailed and contextual and exultory. But they can't be aggregated the way data can. You can keep track of a genre or two or five this way, but not 20. Not 100. I've been monitoring hundreds of genres every week, for years. Now I am as lost as you.
Between the Echo Nest and then, via acquisition, Spotify, I spent 12 years doing a slowly mutating job of trying to use data and math and computers to help all the world's music self-organize. It seems to be the unanimous opinion of people who send me nice notes on email and Twitter and LinkedIn that I did valuable things at Spotify and from Spotify, and that laying me off was some combination of corporate error and public tragedy. I don't think this is merely kindness. Over that time I created or improved a lot of things by direct individual effort, including Daily Mix, This Is artist playlists, Fans Also Like, a genre system, fraud and abuse detection, many pieces of Spotify Wrapped, more internal tools and analytics and prototypes than you can probably imagine, and a public web-temple to music exploration and the discovery of joy.  

I am aware, of course, that people telling me they appreciate what I did is a clear and heartening demonstration of empathetic selection bias. If you didn't care about my work, then it isn't news that I'm not going to be doing it, and doesn't require your comment. It's tempting to imagine that there's somebody at Spotify who actually disagrees with this, and has been waiting for years for an opportunity to replace my uncooperative insistence on using math to make musical sense with something more acquiescent, willing to say "content" instead of "music" and celebrate 0.05% average-metric nudges without asking to see the distributions under the averages and stop posing moral objections to profit-margin KPIs.  

But probably it's far worse than that: There was no enemy, there was no purpose. I didn't lose a heroic battle, I lost a meaningless lottery. A no-warning 1500-person layoff probably cannot be done "well". I see co-workers who were also laid off that had been at Spotify for 12, 13, 14 years, and who thus must have been there in the basement with Daniel and Martin at the beginning. If there is anybody who can take a big company back to its resourceful small-company past-life, it's the people who were literally part of it. Surely you don't lay off the people with the very qualities you're supposedly trying to recapture unless you genuinely can't help it. I did a lot more things inside Spotify than things you could see from outside, and the pragmatic corporate arguments against laying me off needn't have invoked the public good at all. Public loss is collateral damage from capitalism operating for capital's sake.  

Meanwhile, here is the situation: everynoise.com is cut off from data updates, and I expect this will not change. The processes I left running are still running, so the missing data is probably all waiting in dark staging servers, wondering when it will finally be summoned into the light. It won't. The Approaching Worms of Xmas will never reach it this year. 2023 Around the World, my deliberate celebration of full calendar years, will have to be gallingly content with 11-month provisional results. Anything static will remain, in its current state.  

My automated playlists, on the other hand, get updated through Spotify-internal systems, and are still operating. I think it's likely that they'll be spared for the holidays, but if you care about any of those, you should take any further updates as gifts. At best, nobody at Spotify will bother to figure out how my automation actually functions, and everything will be left running until they're ready to turn the whole system off again with one big switch. At worst, tomorrow something will break that nobody knows how to fix or even debug, and that will be it. I don't normally claim that fault-tolerant engineering is one of my core competencies, so it will be a minor triumph if my automation survives long enough to get killed.  

I have some time to find a new job, or at least a plan for ongoing health-insurance coverage. My belief in the promise of streaming music is a function of music and humanity, not of Spotify, so certainly my first inclination is to find another way of contributing to its expanding fulfillment of that promise. But of course there's also a part of my brain that occasionally mutters "Um, climate change?" I also have an idea for a second book, which I was going to work on over the holidays, except that I didn't anticipate having to spend some of that time changing present tenses to past in my first book, which still has to survive the next six months of routine cosmic weirdness before it finally exists.  

The job I've been doing, because I did it with personal goals, affected a lot more than my nominal work-hours, and getting myself to stop trying to do it is harder than remote-locking my work laptop, and a lot more complicated. Urges will have to be channeled somewhere. I will probably need a new way to think about my music-listening, and maybe new tools to replace the ones I lost, and I've never been able to listen to music without also writing about it for very long, so I imagine there might be a new form of that, too. But probably not this week. For now I'm going to put Hitsujibungaku on repeat, and try to let the blurry futures resolve a little. I feel basically OK about the last 12 years, I think. They are not invalidated by their sudden end. But I want the next 12 to be better.  

A few of those nice notes that were written (or ranted) in public:
Every Noise at Once Shuts Down? at Kill the DJ
The Day Music Neutrality Died (a bit) at flyctory.
The 6000 Musical Tribes at The Limited Times, which is a translation of Las 6.000 tribus musicales at El País.
Spotify Fired the Wrong Person at Venture Music.
Continue Everynoise at community.spotify.com.
The job I used to do at Spotify was to experiment with what could be made out of listening data, but the experiments that worked were then automated to run on appropriate schedules. These stopped working temporarily when my employee account was deactivated, but were revived, and some data-driven daily playlists are updating again. Currently no data updates are making it to everynoise.com, though, and all the big weekly jobs run on Fridays, so it remains to be seen what my ghosts there are still allowed to sing.
everynoise.com is and was a projection of things I worked on at the Echo Nest, and then Spotify. As of this morning, I'm not working there, and I expect most of the things I did will no longer be done. The domain is mine, but the processes that updated the site have already stopped running, and the current server may stop serving at any moment. Once that happens, I will try to bring back at least a wistful memorial to what it was.  

But even failing that, its 10-year history lives on in the Wayback Machine. And music, of course, survives our fragile and temporary machines for organizing it.  

More information when I have it.
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:  

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.
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.
[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  


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  


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.  

**account blocked**  

**account blocked**  


welcome to

Enter your embarrassing question:


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.
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.
Site contents published by glenn mcdonald under a Creative Commons BY/NC/ND License except where otherwise noted.