Add link backups
This commit is contained in:
349
content/journal/dispatch-1-march-2023/craigmod-com-ts8csh.txt
Normal file
349
content/journal/dispatch-1-march-2023/craigmod-com-ts8csh.txt
Normal file
@@ -0,0 +1,349 @@
|
|||||||
|
|
||||||
|
About Craig
|
||||||
|
Books & Essays
|
||||||
|
Talks
|
||||||
|
Membership
|
||||||
|
Shop!
|
||||||
|
“Special Projects” Membership
|
||||||
|
Podcasts:🎧 On Margins & SW945
|
||||||
|
Newsletters:📩 Roden & Ridgeline
|
||||||
|
|
||||||
|
|
||||||
|
Header image for Electric Bike, Stupid Love of My Life
|
||||||
|
|
||||||
|
|
||||||
|
Electric Bike, Stupid Love of My Life
|
||||||
|
|
||||||
|
Reflections on eighteen months of electric bike ownership
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
My electric bike sings, emits a nearly imperceptible hum from its tiny motor. I
|
||||||
|
love its song. A song of peace and magic. Has money ever bought as much delight
|
||||||
|
as the delight of an electric bike?
|
||||||
|
|
||||||
|
The first time I rode one was nearly a decade ago, in Kyoto. The electric bike
|
||||||
|
I rented was huge and unwieldy, but that tug of its motor never left my mind. I
|
||||||
|
went to climb a hill and it felt as if a giant had gently placed his hand on my
|
||||||
|
back and pushed me forward. That stupid smile has been on my face ever since.
|
||||||
|
|
||||||
|
Two years ago I rented another one. This one smaller, lighter, the motor more
|
||||||
|
powerful. I was convinced. This is the way. Eighteen months ago, in the heart
|
||||||
|
of the pandemic, I committed and bought my first electric bike and have never
|
||||||
|
looked back.
|
||||||
|
|
||||||
|
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||||
|
|
||||||
|
Indulge me — a summer afternoon: Soaring down the coast, the ocean to one side
|
||||||
|
and a strand of old pines to the other. The afternoon sun beats down but it
|
||||||
|
feels cool and there’s something irrationally stirring — downright emotional —
|
||||||
|
about the efficiency of this dumb machine beneath my body. The motor looks too
|
||||||
|
small — just a black cylinder on the hub of the wheel. And yet it moves. It
|
||||||
|
sings that song. A subtle hum. A beautiful hum. It makes me want to ride and
|
||||||
|
ride, ridiculous distances, nonsensical distances. I don’t want to get to where
|
||||||
|
I’m going because I want the ride to last longer. I want to linger in this
|
||||||
|
space as long as possible, this space of smooth and efficient movement through
|
||||||
|
the world, gliding in near total mechanical silence, just the sound of rubber
|
||||||
|
on the pavement, wind in my ears, breaking waves, salt, the smell of pine. This
|
||||||
|
is what electric bikes do: They drive you insane with the poetry of the world.
|
||||||
|
|
||||||
|
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||||
|
A strange trio A few of my old bikes: A mamachari, carbon fiber road bike, and
|
||||||
|
Kalavinka
|
||||||
|
|
||||||
|
#So Many Bikes
|
||||||
|
|
||||||
|
All my standing life, I’ve biked. As a kid I rode a K-Mart Huffy to a rusted
|
||||||
|
nub and then managed to nab a Haro Group 1. As an adult, bikes have been one of
|
||||||
|
my few material indulgences (unwittingly, organically). In the past twenty
|
||||||
|
years alone I’ve owned some fifteen bikes. I’ve had aluminum and carbon Bianchi
|
||||||
|
road bikes. I’ve had steel Kalavinka keirin bikes with gorgeous head badges.
|
||||||
|
I’ve had folding Dahon and Birdy BD-1s. I’ve had a handful of beloved brandless
|
||||||
|
throwaway mamacharis — shopping bikes — that have proven hearty and fun in
|
||||||
|
their own ways, and have each died uniquely. I’ve gone out of my way to get a
|
||||||
|
handmade Arrow cruiser from a builder in Ogikubo. I still have a custom orange
|
||||||
|
Moulton that I’ve modified into a single-speed city bomber that goes remarkably
|
||||||
|
fast while floating atop its simple suspension.
|
||||||
|
|
||||||
|
And on and on — bikes. Why? Because as any bike lover will tell you, to be
|
||||||
|
ensorcelled by the bike is to crave one and only one thing: More bike. Each new
|
||||||
|
bike is like riding once again for the first time. Exploring a city on a
|
||||||
|
mamachari is different than a BD-1 is different than a Moulton. All thrilling.
|
||||||
|
The bikes change, and so, too does your relationship to the pavement. My love
|
||||||
|
for bikes has no categorical allegiances; if it has two wheels, and pedals, I’m
|
||||||
|
interested. I want to ride them all.
|
||||||
|
|
||||||
|
A Moulton Tiny, but fast, nearly flawless as a city machine — a Moulton with
|
||||||
|
converted stem, Sugino cranks, coaster brake
|
||||||
|
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||||
|
|
||||||
|
Summers in most of Japan have never been easy. The temperatures England flirted
|
||||||
|
with in 2022 are temperatures Tokyoites have contended with for centuries (and
|
||||||
|
now contend with ones even higher). Crushing heat coupled with suffocating
|
||||||
|
humidity. A three-shower-a-day kinda summer. Watch an Ozu film and observe the
|
||||||
|
languid and supine impulse of its inhabitants during summertime scenes — that’s
|
||||||
|
not affect, it’s survival. In Japan’s August, you simply can’t walk a block
|
||||||
|
without losing most of your moisture.
|
||||||
|
|
||||||
|
Bikes have always helped. A bicycle generates a microclimate with minimal
|
||||||
|
effort. Standing on a street corner you may be soaked, but on a bike, the wind
|
||||||
|
whooshing past, you are crisp(er) and dry(er). An electric bike only amplifies
|
||||||
|
the effect.
|
||||||
|
|
||||||
|
When I was a child I dreamt of having a personal helicopter. Powered by my feet
|
||||||
|
and a bit of magic (certainly not gasoline, oddly, thinking back on it now). I
|
||||||
|
imagined quietly gliding over the city in this tiny contraption, floating from
|
||||||
|
home to video rental shop to diner, stopping by a friend’s house along the way.
|
||||||
|
An electric bike gets me most of the way to this feeling.
|
||||||
|
|
||||||
|
In the past eighteen months I’ve put several thousand kilometers on my electric
|
||||||
|
bikes. It feels like cheating in every best possible way. I live in a seaside
|
||||||
|
town south of Tokyo and traffic can get ridiculous, its ancient roads sized for
|
||||||
|
horses, not cars. The electric bike swoops between and alongside these stale
|
||||||
|
processions of heat and burning fuel. Drifting behind a gas-powered scooter or
|
||||||
|
moped feels like observing some Victorian contraption — inefficient and loud
|
||||||
|
and clunky and burdensome and pollutant. And not much faster (often much
|
||||||
|
slower) or more useful than an electric bike.
|
||||||
|
|
||||||
|
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||||
|
A Vanmoof and a BESV My friend's S3 and my BESV (the X3 looks like a slightly
|
||||||
|
smaller version of the S3)
|
||||||
|
|
||||||
|
#Electrics
|
||||||
|
|
||||||
|
I own two electric bikes. My first purchase was the strangely named BESV PSA1 —
|
||||||
|
which is a smaller wheeled (20"), rear-wheel drive machine, with mostly
|
||||||
|
off-the-shelf components allowing you to customize it to your liking. ^1 And
|
||||||
|
then, because I was so enamored by the BESV — so seduced by its small motor of
|
||||||
|
umph, so wanting more and different electric bike experiences — I went and
|
||||||
|
picked up a front-wheel drive Vanmoof X3 — the smaller-wheeled brother (24") to
|
||||||
|
Vanmoof’s (quite frankly) giant S3 — just a few months later.
|
||||||
|
|
||||||
|
I love them both like damaged brothers, because both of these bikes are flawed
|
||||||
|
in frustrating ways.
|
||||||
|
|
||||||
|
The electronic brain on the BESV is as dumb as they come.^2 The settings reset
|
||||||
|
each time you turn the bike on. The acceleration curves feel unrefined —
|
||||||
|
herky-jerky, you might say. Its app is the worst app I have on my phone — badly
|
||||||
|
designed, nearly functionally useless, clearly engineered without love. And
|
||||||
|
yet. Despite these flaws I put hundreds of kilometers on this thing in the
|
||||||
|
first month. The front and rear suspension turn every road to glass, and are
|
||||||
|
even fine for dirt trails; I find myself hunting down paths through parks I’d
|
||||||
|
never otherwise think about. Suddenly every hilly road is a thing demanding to
|
||||||
|
be explored. Up up up the little machine yells, and you follow its command.
|
||||||
|
|
||||||
|
Guests who stay at my studio are given the BESV to ride. We take it down the
|
||||||
|
coast. It never fails to amaze. One friend felt compelled to pet it upon
|
||||||
|
dismount, saying, Good job, buddy, so quick and deep was the affection for the
|
||||||
|
thing.
|
||||||
|
|
||||||
|
The Vanmoof is much smarter — the brain and software within it are refined, the
|
||||||
|
app good, the acceleration curves smooth — but the bike is all custom
|
||||||
|
components, and they aren’t the highest quality at that. The automatic shifting
|
||||||
|
mechanism on mine failed twice in the first two months, requiring shipping the
|
||||||
|
bike to the Vanmoof store.^3 The seat post bolt broke off in the post. The
|
||||||
|
original plastic pedals felt cheap and flimsy (pedals are one of the few things
|
||||||
|
you can swap for your own). The aluminum frame is too stiff for the speed the
|
||||||
|
bike generates — it can feel like you’ve been rattled to death after a bumpy
|
||||||
|
road. (And stiffness mitigation by lowering tire pressure seems to only
|
||||||
|
increase possibility of puncture.) But, more than all that, the design of the
|
||||||
|
bike has a dangerous fundamental flaw: The bottom bracket is simply too low.
|
||||||
|
|
||||||
|
Of all my many, many bikes, I’ve never had a pedal bottom out. On this Vanmoof
|
||||||
|
X3? Dozens of times. Most critically during a turn at speed — the pedal hit the
|
||||||
|
pavement, jumped the bike sideways, and sent me flying. It’s the only bad crash
|
||||||
|
I’ve had in decades. So I’ve had to modify the way I ride — no pedaling into or
|
||||||
|
out of turns, hyper awareness of deviations in lateral road slope — because,
|
||||||
|
despite all this, I can’t stop riding this stupid thing. It sings — that hum.
|
||||||
|
It is joy. I reach for it daily and it takes me around the peninsula and makes
|
||||||
|
me happy to be alive.
|
||||||
|
|
||||||
|
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||||
|
BESV @ Lee's Bread, Oiso I've written about three electric bike rides for
|
||||||
|
Papersky Magazine: Misaki, Oiso, and Yokosuka.
|
||||||
|
|
||||||
|
Allow me to share a dirty secret: More often than not, at midnight I can’t
|
||||||
|
repress the impulse — I have to take a bike out. Out the bike comes and
|
||||||
|
together we head into the empty streets of my town and hum our way all over,
|
||||||
|
visiting temples in total silence. There are no cars. Often no people. It feels
|
||||||
|
illicit — this slipping around town, this sliding into temple parking lots in
|
||||||
|
the shroud of the night, looking at their old beams, feeling ten years old and
|
||||||
|
grateful for both the ability and awareness to be doing just this very thing at
|
||||||
|
this very moment.
|
||||||
|
|
||||||
|
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||||
|
|
||||||
|
I’ve long since posited world peace could be achieved if you bought everyone in
|
||||||
|
the world a bike, but now I want those bikes to be electric. I want everyone to
|
||||||
|
feel this silliness, this punch-drunk stupidity of pure love, this sense of
|
||||||
|
cheating the rules, the norms, this sense of ever-present delight. At our
|
||||||
|
worst, humans mindlessly consume, sear the earth and each other, fill our
|
||||||
|
bodies with poisons. At our best we invent electric bikes. Batteries have
|
||||||
|
gotten more efficient, motors smaller and more powerful. The last decade has
|
||||||
|
brought great efficiency to these machines, and the next ten years will only
|
||||||
|
double down on these gains. Electric bike numbers are up, year over year over
|
||||||
|
year. Tremendously so. Those who know, proselytize. We can’t help it. The charm
|
||||||
|
is too great. The game non- zero sum. The more people who know, the better the
|
||||||
|
world. It’s a wild notion, this sense of goodness to be had if you just reach
|
||||||
|
out for it. Goodness with no real downside. Like solar panels or wind turbines,
|
||||||
|
electric bikes are machines that buoy the spirit and the earth.
|
||||||
|
|
||||||
|
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||||
|
|
||||||
|
Buy the best electric bike you can within your budget. Stretch if possible.
|
||||||
|
Usually, the more you spend the lighter the machine, the more powerful the
|
||||||
|
motor, the longer-lasting the battery. Depending on which country you live in
|
||||||
|
top speeds will differ. In Japan the bike’s are capped at 24km/h. In America,
|
||||||
|
32km/h. Some places only allow for pedal-assist — meaning the motor only works
|
||||||
|
when pedaling. Others allow throttles, blurring the line between bike and
|
||||||
|
scooter. Laws will change in the coming years as more people adopt the machines
|
||||||
|
and cities themselves adapt. This is just the start. Ten years ago it was
|
||||||
|
fairly rare to see an electric bike around Tokyo. Today, it seems as if every
|
||||||
|
parent hauling their kids is doing so electrically.
|
||||||
|
|
||||||
|
A good strategy: Find a local bike shop that will let you try out several
|
||||||
|
electric bikes. Some have front-hub motors, others rear-hub motors. Others, the
|
||||||
|
motor sits in the center, between the cranks. Each has a subtly different feel.
|
||||||
|
Going up a hill, a front-motor’d machine may skip or slip as you pull back on
|
||||||
|
the handlebars, but on flat land will feel more like being tugged through the
|
||||||
|
world.
|
||||||
|
|
||||||
|
Sure, electric bikes aren’t cheap. But I believe they’re a rare object to be
|
||||||
|
well worth the cost. This in spite of their annoying flaws, their often bad
|
||||||
|
software, their defective geometries. Because they open the world. Whatever
|
||||||
|
world may have been nearby, an electric bike brings it nearer. This is worth
|
||||||
|
more than you might estimate. These bikes sing their little songs and the smile
|
||||||
|
on your face makes you look like a village idiot, but what a wonderful idiot to
|
||||||
|
be.
|
||||||
|
|
||||||
|
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||||
|
|
||||||
|
A summer night: Biking home alongside a river. The air is thick with humidity
|
||||||
|
and cicadas vibrate wildly in the distance. The moon is out. My choices:
|
||||||
|
straight home along the shimmering moonlit river, or take a detour, up into the
|
||||||
|
dark mountains, doubling the distance. To my surprise, I choose the mountains
|
||||||
|
almost every time. More! That tiny child who fantasized about helicopters
|
||||||
|
yells. More of this, whatever this is. More more more. And so I feed that
|
||||||
|
impulse, an impulse generated and nurtured by the electric bike. Into the
|
||||||
|
shadow mountains we go, up, pushed by the hand of that giant, always present,
|
||||||
|
always ready to help. It is a ridiculous thing. A thing of peace and magic. An
|
||||||
|
owl hoots. The smile has never left my face.
|
||||||
|
|
||||||
|
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||||
|
|
||||||
|
#Noted:
|
||||||
|
|
||||||
|
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||||
|
|
||||||
|
1. I upgraded my BESV to an SRAM drivetrain and Paul brake levers and Klamper
|
||||||
|
disc calipers, some MKS pedals, and a set of Brooks grips and saddle and it
|
||||||
|
feels wonderful through and through. These Paul Klampers are mechanical.
|
||||||
|
The Vanmoof uses (generic?) hydraulic brakes. After thousands of
|
||||||
|
kilometers, my conclusion is: hydraulics feel nice, but they are fussy (and
|
||||||
|
perhaps Vanmoof’s chosen components are sub-optimal) and difficult (?) to
|
||||||
|
tune on your own. In the end, I just don’t think they’re worth it. Too
|
||||||
|
“delicate.” The Pauls feel as fresh today as the day I put them on, whereas
|
||||||
|
the hydraulics have required much bikeshop tuning over the course of the
|
||||||
|
last eighteen months. Were the Vanmoof more flexible, I’d happily swap out
|
||||||
|
for mechanicals. This lack of flexibility is a bummer because, unlike an
|
||||||
|
Apple iPhone, for example, where the components tend to be best of class
|
||||||
|
(think: modem, CPU, camera unit, etc), the physical components on a Vanmoof
|
||||||
|
most definitely aren’t — nor do they offer the option to pay more to get
|
||||||
|
better components. ↩︎
|
||||||
|
|
||||||
|
2. Oh, how I wish this thing was open source, hackable — because it’s so close
|
||||||
|
to great. Sadly — and I don’t know how else to frame this — it feels like
|
||||||
|
the engineers behind the software don’t ride bikes. At least not this one.
|
||||||
|
The software flaws are so fundamentally obvious, that anyone who had a)
|
||||||
|
access to the code, and b) rode the bike, couldn’t NOT fix these obvious
|
||||||
|
issues. What I really wish, though, is that I could slap the Vanmoof brain
|
||||||
|
onto the BESV body and, well, then we’d be in Electric Bike Elysium. ↩︎
|
||||||
|
|
||||||
|
3. I’ve since learned — the drive train of the Vanmoof is not to be “ridden”
|
||||||
|
like a “bike” but rather, “feathered” like a delicate sand castle — assume
|
||||||
|
the gears could explode at any moment and apply the least amount of
|
||||||
|
pressure you can; the motor is strong enough to take care of most of the
|
||||||
|
rest. In this way, the Vanmoof feels more like a moped that uses “pedal
|
||||||
|
assist” as a suggestion than a pure electric-assist bike — a smart way to
|
||||||
|
get around motorcycle laws in most countries, which I assume is the main
|
||||||
|
point. Not to say you don’t get a workout on the Vanmoof, you do, but not
|
||||||
|
nearly as much as the more classically committed BESV — which really does
|
||||||
|
require you to pedal.
|
||||||
|
|
||||||
|
Maybe this is a good place to bring up the question: Why not just get an
|
||||||
|
electric scooter? I think it mainly comes down to flexibility and
|
||||||
|
philosophy. With a pedal assist bike (even if the pedaling required is
|
||||||
|
minimal) you simply have more flexibility in parking, in riding, in
|
||||||
|
“lightness” of transportation, than with an electric scooter. Also:
|
||||||
|
Insurance costs, maintenance, and higher base cost. And philosophically,
|
||||||
|
being able to still use the bike as a “bike” without power feels like an
|
||||||
|
aspect of these machines we shouldn’t be so quick to toss aside. ↩︎
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
This essay, published September 2022. Thoughts? Email me@craigmod.com.
|
||||||
|
|
||||||
|
Craig Mod, his head, floating at the bottom of the article
|
||||||
|
|
||||||
|
Craig Mod is a writer and photographer based in Japan. He's the author of Kissa
|
||||||
|
by Kissa and a MacDowell, Ragdale, and VCCA writing fellow. His essays and
|
||||||
|
articles have appeared in Eater, The Atlantic, California Sunday Magazine,
|
||||||
|
Wired, Aeon, New Scientist, Virginia Quarterly Review, The New Yorker, The New
|
||||||
|
York Times, The Morning News, Codex: Journal of Typography, and elsewhere. He
|
||||||
|
writes newsletters, oh yes, newsletters: Roden & Ridgeline.
|
||||||
|
|
||||||
|
The work on this site is supported in part by paid memberships.
|
||||||
|
|
||||||
|
Whatever you do, don't follow @craigmod on Twitter or Instagram.
|
||||||
|
|
||||||
|
Subscribe to my newsletters
|
||||||
|
|
||||||
|
Join some ~30,000 other subscribers.
|
||||||
|
|
||||||
|
Roden: photography × literature × tech × film (monthly)
|
||||||
|
Ridgeline: walking × Japan (weekly)
|
||||||
|
|
||||||
|
Always one-click to unsubscribe.
|
||||||
|
|
||||||
|
[ ]
|
||||||
|
[*] Roden (monthly)
|
||||||
|
[*] Ridgeline (weekly)
|
||||||
|
Subscribe
|
||||||
|
Popular Essays
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
COVID-19 and Walking Japan
|
||||||
|
|
||||||
|
What it's like to walk across Japan during the pandemic
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Them Post-walk Blues
|
||||||
|
|
||||||
|
Considering life after a big walk
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Welcome Back to Our COVID Loop
|
||||||
|
|
||||||
|
Back in lockdown, back on the Ridgeline express
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
That Shinkansen Whoosh
|
||||||
|
|
||||||
|
Modernity flowing past rice fields
|
||||||
|
|
||||||
|
[ ]
|
||||||
|
|
||||||
|
© 2001 - 2023, Craig Mod
|
||||||
|
|
||||||
|
Twitter Instagram Mastodon RSS
|
||||||
|
|
||||||
|
[piwik]
|
||||||
|
|
||||||
@@ -24,6 +24,14 @@ Reading:
|
|||||||
|
|
||||||
Links:
|
Links:
|
||||||
|
|
||||||
* [Electric Bike, Stupid Love of My Life — by Craig Mod](https://craigmod.com/essays/electric_bikes/)
|
* [Electric Bike, Stupid Love of My Life — by Craig Mod][1][^1-backup]
|
||||||
* [Programming is a Pop Culture – Baldur Bjarnason](https://www.baldurbjarnason.com/2022/programming-is-a-pop-culture/)
|
* [Programming is a Pop Culture – Baldur Bjarnason][2][^2-backup]
|
||||||
* [Julia Cameron Wants You to Do Your Morning Pages - The New York Times](https://www.nytimes.com/2019/02/02/style/julia-cameron-the-artists-way.html)
|
* [Julia Cameron Wants You to Do Your Morning Pages - The New York Times][3][^3-backup]
|
||||||
|
|
||||||
|
[1]: https://craigmod.com/essays/electric_bikes/
|
||||||
|
[2]: https://www.baldurbjarnason.com/2022/programming-is-a-pop-culture/
|
||||||
|
[3]: https://www.nytimes.com/2019/02/02/style/julia-cameron-the-artists-way.html
|
||||||
|
|
||||||
|
[^1-backup]: <a href="craigmod-com-ts8csh.txt">Backed up 2023-04-03 23:56:02 -0400</a>
|
||||||
|
[^2-backup]: <a href="www-baldurbjarnason-com-7p5031.txt">Backed up 2023-04-03 23:57:18 -0400</a>
|
||||||
|
[^3-backup]: <a href="www-nytimes-com-tq2xdi.txt">Backed up 2023-04-03 23:57:38 -0400</a>
|
||||||
@@ -0,0 +1,610 @@
|
|||||||
|
• Essays
|
||||||
|
• Newsletter
|
||||||
|
• Ebook
|
||||||
|
• Contact
|
||||||
|
|
||||||
|
Baldur Bjarnason
|
||||||
|
|
||||||
|
Web dev at the end of the world, from Hveragerði, Iceland
|
||||||
|
|
||||||
|
I’m available as a consultant. I also have a book out.
|
||||||
|
|
||||||
|
21 November 2022
|
||||||
|
|
||||||
|
Programming is a Pop Culture
|
||||||
|
|
||||||
|
(What follows is an extract from Out of the Software Crisis, lightly edited to
|
||||||
|
work as a blog post.)
|
||||||
|
|
||||||
|
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||||
|
|
||||||
|
|
||||||
|
So I think what happened is computing has turned into pop culture and the
|
||||||
|
universities are not helping in general, at least not in the US.
|
||||||
|
|
||||||
|
So, Cicero---anybody know a good Cicero quote having to do with the present
|
||||||
|
and past? Let's check your classical education here. So, you know who
|
||||||
|
Cicero was. He was one of those old Roman guys.
|
||||||
|
|
||||||
|
So, Cicero once wrote: 'He who knows only his own generation remains
|
||||||
|
forever a child.'
|
||||||
|
|
||||||
|
Programming and Scaling (Alan Kay, 2011)
|
||||||
|
|
||||||
|
The programming pop culture defines change—any change—as progress. Most
|
||||||
|
developers, myself included, have a fascination with novelty. If it’s new, then
|
||||||
|
it must be an improvement. You even hear this stated outright as an argument by
|
||||||
|
developers: it’s newer and therefore better. Trends in software development are
|
||||||
|
rarely based on objective observation or sensible practice. This endless
|
||||||
|
chasing of trends leads to projects being needlessly rewritten, code being
|
||||||
|
abandoned, and new projects being started when fixing the bugs in an old
|
||||||
|
project would have done the same. The stocks of the software development system
|
||||||
|
are flushed out at a moment’s notice simply because the developers found
|
||||||
|
something shinier.
|
||||||
|
|
||||||
|
Experienced developers are aware of this tendency in themselves and work to
|
||||||
|
mitigate it, but younger developers are often under the mistaken impression
|
||||||
|
that this is how software development works. Unless they can pare back this
|
||||||
|
tendency or are matched with teammates who hold them back, this tendency can
|
||||||
|
lead to immense destruction of value for an organisation.
|
||||||
|
|
||||||
|
Pop cultures favour the visual aesthetic of the day. We all know what sort of
|
||||||
|
aesthetic designers commonly favour. Small, low-contrast text, lots of
|
||||||
|
whitespace, no pure whites or pure blacks (just greys). The details vary with
|
||||||
|
fashion, but each generation of designers has a preferred visual aesthetic.
|
||||||
|
That aesthetic tests poorly; the text is illegible; the layout doesn’t have
|
||||||
|
enough contrast. The information density is so sparse it’s effectively
|
||||||
|
non-existent.
|
||||||
|
|
||||||
|
Looks pretty, though.
|
||||||
|
|
||||||
|
Coders have a similar tendency, their preferred aesthetic is just a bit
|
||||||
|
different, but as with designers, it tests horribly when put in front of
|
||||||
|
genuine users. The exact details of the preferred aesthetic tend to vary from
|
||||||
|
generation to generation. One group prefers light-on-dark text (despite not
|
||||||
|
suffering from conditions that benefit from dark mode) and unusable
|
||||||
|
hyper-complex layouts where everything is configurable. Another group goes for
|
||||||
|
ultra-minimalism where nothing is shown by default. You constantly scrub around
|
||||||
|
and hunt for a button, a widget—anything that even vaguely resembles an
|
||||||
|
affordance. This is usually not an issue if you have designers on the team. If
|
||||||
|
you’re letting the programmers design the user interface or are a programmer
|
||||||
|
designing a user interface, you need to be aware of it.
|
||||||
|
|
||||||
|
But this adherence to a specific aesthetic isn’t limited to designs. It’s also
|
||||||
|
an issue when it comes to the code itself.
|
||||||
|
|
||||||
|
The programming pop culture favours specific code aesthetics based on the
|
||||||
|
trends of the day. I’m not talking about code style or formatting. The code in
|
||||||
|
a project should adhere to a single style, simple as that. The issue is that
|
||||||
|
the programming pop culture demands that code exhibit the latest popular
|
||||||
|
aesthetics of rigour, formality, and cleverness. Whether the code actually is
|
||||||
|
rigorous, formal, or clever matters less. A few years ago, as the popularity of
|
||||||
|
the Ruby programming language peaked, a certain dynamism and trickery were en
|
||||||
|
vogue. It didn’t matter if you were writing in Ruby, JavaScript, or
|
||||||
|
Objective-C. Your code had to have a level of “magic” to it. Metaprogramming,
|
||||||
|
syntax-hacking languages to create ad hoc Domain-Specific Languages, tricks
|
||||||
|
with extreme late binding, and more were frequent topics on developer weblogs
|
||||||
|
and forums. Even a phrase like “objective-c runtime metaprogramming” will date
|
||||||
|
you to a specific generation of native app developers almost down to a single
|
||||||
|
year.
|
||||||
|
|
||||||
|
As with all of these pop culture trends in programming, this led to unreadable
|
||||||
|
code that was impossible to work with or fix as soon as it faded from popular
|
||||||
|
consciousness.
|
||||||
|
|
||||||
|
The current trend is towards the aesthetics of correctness. Everything has to
|
||||||
|
look like it has strong or static typing. It doesn’t have to really have static
|
||||||
|
typing. That can all be made up after the fact in a declaration file. It merely
|
||||||
|
needs to have the aesthetics of types. Type annotations everywhere,
|
||||||
|
implementing logic through type system trickery, and forcing any and all
|
||||||
|
dynamism out of the system in the name of correctness is the name of the game.
|
||||||
|
|
||||||
|
A part of this trend is the unpopularity of the approaches and languages that
|
||||||
|
are seen as less rigorous. CSS is dropped in favour of statically typed
|
||||||
|
CSS-in-JS approaches. HTML is dropped in favour of a strict inline XML-like
|
||||||
|
markup format called JSX. Just a few years ago, everybody in web development
|
||||||
|
hated and dropped XML and XHTML specifically because it was too strict and felt
|
||||||
|
less dynamic and flexible than HTML. At some point, pop culture will bore of
|
||||||
|
this and swing its attention back the other way.
|
||||||
|
|
||||||
|
It’s a fashion industry. Trends come; trends go. The lack of historical
|
||||||
|
awareness is considered by most to be a feature.
|
||||||
|
|
||||||
|
This rigour is useful in moderation. Static typing does prevent bugs. Usually,
|
||||||
|
they are the same sort of bugs unit testing prevents. Both have immense value
|
||||||
|
as tools to manage your software development. Currently, the fashion is to
|
||||||
|
favour static typing over unit testing for establishing a certain base level of
|
||||||
|
correctness in your code. At some point, they are likely to switch again. They
|
||||||
|
have a couple of times in the past. That you could use both at the same time
|
||||||
|
and get the benefits of both doesn’t enter the discourse. Static typing with
|
||||||
|
compile-time correctness checks has its uses. So do dynamism, extreme late
|
||||||
|
binding, and metaprogramming. Most of these approaches can be used together,
|
||||||
|
but that isn’t how pop culture works. Pop culture demands there be only one
|
||||||
|
winner at a time. Choose one, not whichever works the best at each time.
|
||||||
|
|
||||||
|
Product development can’t indulge in being pop culture. Be wary of these
|
||||||
|
popularity contests.
|
||||||
|
|
||||||
|
These issues with programming culture aren’t new.
|
||||||
|
|
||||||
|
Jamie Zawinski calls it the “Cascade of Attention-Deficit Teenagers” model. We
|
||||||
|
can’t do much to change the nature of the field by now—Alan Kay has certainly
|
||||||
|
tried—but we can mitigate the harm done by the trend-seeking. We can work to
|
||||||
|
ensure that everybody on the team, programmers and designers, is aligned, and
|
||||||
|
have the same understanding of what matters and how to accomplish it.
|
||||||
|
|
||||||
|
For that, you need everybody to understand the context they are working in—the
|
||||||
|
works of their field and how they are received. You need to develop taste and
|
||||||
|
understanding.
|
||||||
|
|
||||||
|
You need research.
|
||||||
|
|
||||||
|
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||||
|
|
||||||
|
Bonus Alan Kay quote on programming as a pop culture that I didn’t include in
|
||||||
|
the book:
|
||||||
|
|
||||||
|
But pop culture holds a disdain for history. Pop culture is all about
|
||||||
|
identity and feeling like you’re participating. It has nothing to do with
|
||||||
|
cooperation, the past or the future—it’s living in the present. I think the
|
||||||
|
same is true of most people who write code for money. They have no idea
|
||||||
|
where [their culture came from]—and the Internet was done so well that most
|
||||||
|
people think of it as a natural resource like the Pacific Ocean, rather
|
||||||
|
than something that was man-made.
|
||||||
|
|
||||||
|
Alan Kay, Dr. Dobb’s Interview with Alan Kay
|
||||||
|
|
||||||
|
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||||
|
|
||||||
|
Out of the Software Crisis
|
||||||
|
|
||||||
|
Out of the Software Crisis by Baldur Bjarnason
|
||||||
|
|
||||||
|
Software projects keep failing, not because we don’t have the right team or
|
||||||
|
tools but because our software development system is broken. Out of the
|
||||||
|
Software Crisis is a guide to fixing your software projects with
|
||||||
|
systems-thinking making them more resilient to change and less likely to fail.
|
||||||
|
|
||||||
|
Systems-Thinking For Software Projects
|
||||||
|
|
||||||
|
WTF is a Framework?
|
||||||
|
|
||||||
|
The response to Out of the Software Crisis has been amazing
|
||||||
|
|
||||||
|
Join the Newsletter
|
||||||
|
|
||||||
|
Subscribe to the Out of the Software Crisis newsletter to get my weekly (at
|
||||||
|
least) essays on how to avoid or get out of software development crises.
|
||||||
|
|
||||||
|
Join now and get a free PDF of three bonus essays from Out of the Software
|
||||||
|
Crisis.
|
||||||
|
|
||||||
|
[ ]
|
||||||
|
Subscribe
|
||||||
|
|
||||||
|
We respect your privacy.
|
||||||
|
|
||||||
|
Unsubscribe at any time.
|
||||||
|
|
||||||
|
Archive
|
||||||
|
|
||||||
|
Writing
|
||||||
|
|
||||||
|
• GDPR and American AIs 3 April 2023
|
||||||
|
• Regulating AI (plus links & notes) 27 March 2023
|
||||||
|
• AI summaries and AI healthcare (links & notes) 20 March 2023
|
||||||
|
• Keeping up with and assessing AI research (links & notes) 13 March 2023
|
||||||
|
• Waiting for the AI Godot (Links & Notes) 6 March 2023
|
||||||
|
• Copyright, Situating Search, and other links & notes 27 February 2023
|
||||||
|
• Deno, Shakespeare's Emoticon, Return to Office, and other links and notes
|
||||||
|
20 February 2023
|
||||||
|
• Book production, AI, Single-Page-Apps, and other links and notes 13
|
||||||
|
February 2023
|
||||||
|
• Some thoughts on how to make a book, three months after I made one 10
|
||||||
|
February 2023
|
||||||
|
• AI is a Hail Mary pass and other links & notes 6 February 2023
|
||||||
|
• EU and copyright protections for AI-generated works and other notes 30
|
||||||
|
January 2023
|
||||||
|
• On the Layoffs, Narcissists, and Other Links & Notes 23 January 2023
|
||||||
|
• Madeline, Existential Terror and other links & notes 16 January 2023
|
||||||
|
• Out of the Software Crisis Available on Kindle 28 December 2022
|
||||||
|
• A lot can happen in a month: on AI art and the fediverse 16 December 2022
|
||||||
|
• The response to Out of the Software Crisis has been amazing 5 December 2022
|
||||||
|
• Programming is a Pop Culture 21 November 2022
|
||||||
|
• WTF is a Framework? 18 November 2022
|
||||||
|
• Theory-building and why employee churn is lethal to software companies 16
|
||||||
|
November 2022
|
||||||
|
• Great apps are rare 15 November 2022
|
||||||
|
• (Released!) Out of the Software Crisis: Systems-Thinking for Software
|
||||||
|
Projects 14 November 2022
|
||||||
|
• Out of the Software Crisis: the ebook is imminent! 11 November 2022
|
||||||
|
• I wrote a book – now you must suffer with me 26 October 2022
|
||||||
|
• I’m offering research, writing, and notetaking coaching for techies and
|
||||||
|
programmers 17 October 2022
|
||||||
|
• Playacting genius: the performative logic of reasoning from first
|
||||||
|
principles 18 September 2022
|
||||||
|
• I don't care how you web dev; I just need more better web apps 4 July 2022
|
||||||
|
• Essay Archive 2 June 2022
|
||||||
|
• On online collaboration and our obligations as makers of software 2 June
|
||||||
|
2022
|
||||||
|
• The different kinds of notes 6 May 2022
|
||||||
|
• What I learned about markdown from interviewing a bunch of people 6 May
|
||||||
|
2022
|
||||||
|
• The Colophon Cards User Survey 2 February 2022
|
||||||
|
• How to keep up with web development without falling into despair 31 January
|
||||||
|
2022
|
||||||
|
• Let's just not talk about 2021 and look forward instead 5 January 2022
|
||||||
|
• Making Colophon Cards 29 November 2021
|
||||||
|
• What do I need to read to be a great at CSS? 19 October 2021
|
||||||
|
• The event listening toolkit: five ways to get out of an event handling mess
|
||||||
|
11 October 2021
|
||||||
|
• FormData and fetch, why is serialising a form such a pain? 29 September
|
||||||
|
2021
|
||||||
|
• The Single-Page-App Morality Play 6 September 2021
|
||||||
|
• Software Crisis 2.0 25 August 2021
|
||||||
|
• Lessons in Interactivity, 2021 redux 13 August 2021
|
||||||
|
• Nobody gives a hoot about groupthink 29 July 2021
|
||||||
|
• Spontant: in praise of grey 26 July 2021
|
||||||
|
• Ways of reading without the influence of community 6 July 2021
|
||||||
|
• The Open-Source Software bubble that is and the blogging bubble that was 11
|
||||||
|
May 2021
|
||||||
|
• You are what you do, not what you say or write 4 May 2021
|
||||||
|
• The Curious Case Of The Crashing Conic Gradient And How I Used A Technique
|
||||||
|
I Learned In The 90s To Fix It 28 April 2021
|
||||||
|
• 136 facts every web dev should know before they burn out and turn to
|
||||||
|
landscape painting or nude modelling 21 April 2021
|
||||||
|
• I’m available for projects and other work 20 April 2021
|
||||||
|
• Which type of novelty-seeking web developer are you? 31 March 2021
|
||||||
|
• Every Day; a Fair Warning (You Should Read These Articles) 3 March 2020
|
||||||
|
• Weeknote 3 - Resistance and the dull blade 10 February 2020
|
||||||
|
• Weeknote 2 (2020) - News, Bad News, and Star Wars 2 February 2020
|
||||||
|
• Weeknote 1 (2020) - Ending the hiatus 26 January 2020
|
||||||
|
• The Ed Tech Conundrum 2 January 2020
|
||||||
|
• Thinking about the past, present, and future of web development 1 January
|
||||||
|
2020
|
||||||
|
• The Web Falls Apart 3 November 2019
|
||||||
|
• Weeknote 19 ─ blog redesign and changes at work 27 October 2019
|
||||||
|
• When life hands you lemonades, sit down and contemplate the meaning of life
|
||||||
|
10 September 2019
|
||||||
|
• Weeknote 18 - Uncertainty and Discomfort 11 August 2019
|
||||||
|
• Web Dev: The Red Queen Wire Mommy of Modern Tech 6 August 2019
|
||||||
|
• Weeknote 16 – Vacation 29 July 2019
|
||||||
|
• Weeknote 15 - Counting Down the Days 1 July 2019
|
||||||
|
• Weeknote 14 - Shadows and DOMs 25 June 2019
|
||||||
|
• Weeknote 13 - The weight of deadlines 16 June 2019
|
||||||
|
• That Web Dev Thing Where Everybody Says Something Clever Involving Toast 15
|
||||||
|
June 2019
|
||||||
|
• SwiftUI, Privacy, macOS, and the Web 9 June 2019
|
||||||
|
• Weeknote 12 - The genres of web media 5 June 2019
|
||||||
|
• The Aesthetics of Concentration 3 June 2019
|
||||||
|
• Weeknote 11 - do I have focus? 29 May 2019
|
||||||
|
• Weeknote 10 - A clear view and more reading 20 May 2019
|
||||||
|
• Weeknote 9 - Being contemplative, finishing a photo project 12 May 2019
|
||||||
|
• Weeknote 8 – Moving, Endgame, and more musings on colour 5 May 2019
|
||||||
|
• Weeknote 7 - Story length and that thing about colour 29 April 2019
|
||||||
|
• Weeknote 6 – Star Trek, rest and spring finally arrives 22 April 2019
|
||||||
|
• Weeknote 5 – Stuff, comics, superheroes, and other nonsense 14 April 2019
|
||||||
|
• Weeknote 4 – TV week with The Expanse 7 April 2019
|
||||||
|
• Weeknote 3 — MVPs, fatigue, and emotional crutches 31 March 2019
|
||||||
|
• Web Development: with great power comes the ability to make great mistakes
|
||||||
|
24 March 2019
|
||||||
|
• Weeknote 2 - Web Development Mistakes, Mary Sues, and Icy Spring 24 March
|
||||||
|
2019
|
||||||
|
• Weeknote 1 18 March 2019
|
||||||
|
• Hitchcock and the author construct 12 February 2019
|
||||||
|
• Seams, Stitches, And The Decline Of The Mac 3 November 2018
|
||||||
|
• Neither Paper Nor Digital Does Active Reading Well 3 September 2018
|
||||||
|
• Focusing on market share blinds you to growth 7 January 2018
|
||||||
|
• The future of Software Development: Just Business Logic 7 January 2018
|
||||||
|
• Remote work is a completely different beast 7 January 2018
|
||||||
|
• Hypertext is still the fundamental model of the web 7 January 2018
|
||||||
|
• Leftover Thoughts From 2017 7 January 2018
|
||||||
|
• Over-engineering is under-engineering 25 November 2017
|
||||||
|
• The process is the thing 23 March 2017
|
||||||
|
• Von Be Don: A few notes on a recent digital publishing project in Iceland
|
||||||
|
19 February 2017
|
||||||
|
• W3C and EME: it isn't about preventing DRM but saving the W3C 14 February
|
||||||
|
2017
|
||||||
|
• Unpopular opinion: dismissing indirect pointers is a mistake 4 February
|
||||||
|
2017
|
||||||
|
• Anger feels like poison 24 January 2017
|
||||||
|
• Is JavaScript more fragile? 7 December 2016
|
||||||
|
• Debating Progressive Enhancement 5 December 2016
|
||||||
|
• The downside of believing in Apple 1 November 2016
|
||||||
|
• A short primer on Icelandic politics on the day of the 2016 election 29
|
||||||
|
October 2016
|
||||||
|
• The Tragedy/Farce of the Open Web according to journalists 18 October 2016
|
||||||
|
• Notes on debating for the web development community 17 October 2016
|
||||||
|
• Addendum on loose coupling and the iOS App Store 11 October 2016
|
||||||
|
• Idle thoughts on modularity and loose coupling in digital media 9 October
|
||||||
|
2016
|
||||||
|
• When fear is rational 24 June 2016
|
||||||
|
• Once upon a time, I couldn't imagine a better word processor than Word 7
|
||||||
|
June 2016
|
||||||
|
• A thought to consider 24 May 2016
|
||||||
|
• A few thoughts on standardisation, W3C, and the IDPF 16 May 2016
|
||||||
|
• Filling in the gaps – the dynamics of zero marginal cost 21 April 2016
|
||||||
|
• Which CMS/blog system would you choose? 12 April 2016
|
||||||
|
• A few simplified points on web and document security 30 March 2016
|
||||||
|
• Judge the work 21 January 2016
|
||||||
|
• Why did Paul Graham argue against equality? 13 January 2016
|
||||||
|
• Purpose, Joy, Capability 4 January 2016
|
||||||
|
• You can't fix the App Store, so here's how you fix it 20 November 2015
|
||||||
|
• Why I am worried about Twitter and why you should be too 4 November 2015
|
||||||
|
• The crossroads or the wilderness 23 October 2015
|
||||||
|
• You can't solve people problems with software 28 September 2015
|
||||||
|
• The discussion about ad blocking is very dumb (but not in the way you
|
||||||
|
think) 18 September 2015
|
||||||
|
• This is not a book, but it is a podcast 10 September 2015
|
||||||
|
• A week of 'This is not a book' 7 September 2015
|
||||||
|
• Launching "This is not a book" – what it is and why you should be
|
||||||
|
interested 1 September 2015
|
||||||
|
• My kingdom for a new bookstore 28 August 2015
|
||||||
|
• Modern software sucks 26 August 2015
|
||||||
|
• The cost versus benefits of disorganised programming power 25 August 2015
|
||||||
|
• Who benefits the most from Open Source Software? 25 August 2015
|
||||||
|
• Sex Apocalypse Later 24 August 2015
|
||||||
|
• Random thoughts on work and that Amazon thing 23 August 2015
|
||||||
|
• Bookmarks – UI flaws and other great capers 14 August 2015
|
||||||
|
• Bookmarks – learnable programming 13 August 2015
|
||||||
|
• Bookmarks – More money for open-source 12 August 2015
|
||||||
|
• Bookmarks – Leaving bosses 11 August 2015
|
||||||
|
• Bookmarks – Promoting other people's work 10 August 2015
|
||||||
|
• Bookmarks – What Would Kamala Khan Do? 7 August 2015
|
||||||
|
• Bookmarks – Trickle down golden geese 6 August 2015
|
||||||
|
• Bookmarks – Hateviews are us 5 August 2015
|
||||||
|
• Bookmarks – Milk it 4 August 2015
|
||||||
|
• Iterating the web away:
|
||||||
|
losing the next generation 4 August 2015
|
||||||
|
• Bookmarks – You haven't been paying attention 3 August 2015
|
||||||
|
• Bookmarks – It's a note card world, we just live in it 31 July 2015
|
||||||
|
• Bookmarks – Just call it Smylfeste 30 July 2015
|
||||||
|
• Bookmarks – That one is shaped like an idiot 29 July 2015
|
||||||
|
• Blogger nostalgia 28 July 2015
|
||||||
|
• Bookmarks – Make it simpler 28 July 2015
|
||||||
|
• Wet streets cause rain and criminal responsibility 27 July 2015
|
||||||
|
• Tweet bookmarks galore 26 July 2015
|
||||||
|
• Random links that catch my fancy, part four of ∞ 23 July 2015
|
||||||
|
• Random links that catch my fancy, part three of ∞ 22 July 2015
|
||||||
|
• Mythic visions of sexuality 21 July 2015
|
||||||
|
• Random links that catch my fancy, part two of ∞ 21 July 2015
|
||||||
|
• Random links that catch my fancy, part one of ∞ 20 July 2015
|
||||||
|
• An exercise for the reader in integration and modularity 17 July 2015
|
||||||
|
• How to read my nonsense 17 July 2015
|
||||||
|
• Is it distributed or just a disorganised hierarchy? 10 July 2015
|
||||||
|
• On the vaunted robustness of the web 10 July 2015
|
||||||
|
• The rules of the game have changed for RSS 10 July 2015
|
||||||
|
• The web app developer's lament 6 July 2015
|
||||||
|
• Other people write about digital media 25 June 2015
|
||||||
|
• The plural of 'Medium' is clearly 'clusterfuck' 25 June 2015
|
||||||
|
• Burnout 24 June 2015
|
||||||
|
• The files Steven Pressfield works with 24 June 2015
|
||||||
|
• iOS 9 content blocking extensions are not a mobile advertising armageddon
|
||||||
|
14 June 2015
|
||||||
|
• Writing the Other:
|
||||||
|
a book that's useful to all writers 3 June 2015
|
||||||
|
• Should I make a WWDC prediction?
|
||||||
|
Yes, let's 3 June 2015
|
||||||
|
• Grim Meathook Present #2 2 June 2015
|
||||||
|
• Other people discuss software quality (spoiler: it sucks) 2 June 2015
|
||||||
|
• Other people talk about startups and entrepreneurship 2 June 2015
|
||||||
|
• A few quick links and thoughts on big web problems 29 May 2015
|
||||||
|
• I really want the Supergirl TV show to be fun 25 May 2015
|
||||||
|
• Our Grim Meathook Present 25 May 2015
|
||||||
|
• The new age of HTML:
|
||||||
|
the web is being torn apart 20 May 2015
|
||||||
|
• Her movie, his name;
|
||||||
|
Mad Max: Fury Road 19 May 2015
|
||||||
|
• We are a violent species 19 May 2015
|
||||||
|
• Toxic environments:
|
||||||
|
inequality in tech is a symptom of something worse 18 May 2015
|
||||||
|
• Where I write about Facebook's Instant Articles 16 May 2015
|
||||||
|
• Facebook and the media:
|
||||||
|
united, they attack the web 15 May 2015
|
||||||
|
• Speeding up decision cycles with rules and heuristics 14 May 2015
|
||||||
|
• You are here #5:
|
||||||
|
UX, design, and CSS as a parasite 14 May 2015
|
||||||
|
• You are here #4:
|
||||||
|
an epic journey through app dev and male bodies 13 May 2015
|
||||||
|
• You are here #3:
|
||||||
|
the glorious wonders of online reading await you 12 May 2015
|
||||||
|
• 2015-05-11-18-39-16 11 May 2015
|
||||||
|
• You are here #2:
|
||||||
|
an artisanal curation of reading material 11 May 2015
|
||||||
|
• You are here #1:
|
||||||
|
a selection of fine links and tweets for your pleasure 10 May 2015
|
||||||
|
• 2015-05-07-00-59-18 7 May 2015
|
||||||
|
• Five publishing-related thoughts on a Friday afternoon 4 May 2015
|
||||||
|
• Why should people read more books? 4 May 2015
|
||||||
|
• How is taxing ebooks as print books supposed to work? 4 May 2015
|
||||||
|
• Kathy Sierra's Badass: Making Users Awesome – the book you all should read
|
||||||
|
4 March 2015
|
||||||
|
• Idle Sunday thoughts about web trends 1 March 2015
|
||||||
|
• Repetition only works in fiction 1 March 2015
|
||||||
|
• The web has covered the basics — that’s why it’ll get harder from now 1
|
||||||
|
March 2015
|
||||||
|
• A draft of a chapter of some thoughts on things. 9 January 2015
|
||||||
|
• Taking stock of 2013 and 2014 31 December 2014
|
||||||
|
• The weather, of course 17 December 2014
|
||||||
|
• Publishing business ideas are a dime a dozen 3 December 2014
|
||||||
|
• EU VAT changes shift the digital landscape 25 November 2014
|
||||||
|
• Money is a poor measure of value 25 November 2014
|
||||||
|
• On conferences 13 November 2014
|
||||||
|
• Crushed by multinationals 12 November 2014
|
||||||
|
• Software as a strategy: prefabricated publishers 7 November 2014
|
||||||
|
• Software as strategy in the ebook world 6 November 2014
|
||||||
|
• The five types of unpublished books 5 November 2014
|
||||||
|
• Four hundred words from Anita Elberse's book "Blockbusters" 4 November 2014
|
||||||
|
• The splintered author 4 November 2014
|
||||||
|
• There is no war between Amazon and Traditional Publishing 3 November 2014
|
||||||
|
• Ebooks suck for learning 10 October 2014
|
||||||
|
• The Poisoning of Social Media: A Reading List 9 September 2014
|
||||||
|
• Wobbly Amazon 10 August 2014
|
||||||
|
• This week's must-read post 24 July 2014
|
||||||
|
• Friends don’t let their friends become authors 10 July 2014
|
||||||
|
• Both at the same time 4 July 2014
|
||||||
|
• So I had to make an ebook cover... 15 April 2014
|
||||||
|
• So long, Readmill, and thanks for all the fish 31 March 2014
|
||||||
|
• What ebook production problems are self-publishers facing? 24 March 2014
|
||||||
|
• Many stories, many truths 13 March 2014
|
||||||
|
• Problem statements for digital publishing research 28 February 2014
|
||||||
|
• To do, to do 21 February 2014
|
||||||
|
• iBooks Author tempts you with bling 20 February 2014
|
||||||
|
• Microsoft Word is a liability 19 February 2014
|
||||||
|
• The print design mentality 18 February 2014
|
||||||
|
• Book contracts 12 February 2014
|
||||||
|
• Intermission: sorting through the banal 5 February 2014
|
||||||
|
• How to create value with a new thing 30 January 2014
|
||||||
|
• HTML is too complex 29 January 2014
|
||||||
|
• The ebook as an API 28 January 2014
|
||||||
|
• My last word on DRM 27 January 2014
|
||||||
|
• Except, except, except 23 January 2014
|
||||||
|
• A thought exercise 22 January 2014
|
||||||
|
• Losing faith in yourself 21 January 2014
|
||||||
|
• Changing your readership mix 20 January 2014
|
||||||
|
• Sex, education, readers, and futures: what works, what doesn't 18 January
|
||||||
|
2014
|
||||||
|
• The various types of readers 17 January 2014
|
||||||
|
• The unevenly distributed ebook future 16 January 2014
|
||||||
|
• Sex, violence, and stílbrot 15 January 2014
|
||||||
|
• Recipe for pundit response to Hugh Howey’s suggestions 14 January 2014
|
||||||
|
• Bling it up for education 13 January 2014
|
||||||
|
• Blogging has trained me to assume you’re stupid 9 January 2014
|
||||||
|
• Ergodic literature 8 January 2014
|
||||||
|
• What I thought I wanted versus what I really wanted 7 January 2014
|
||||||
|
• The mistake of 'enhancing' novels 6 January 2014
|
||||||
|
• Pessimistic ramblings and other fun links (week overview + further reading)
|
||||||
|
4 January 2014
|
||||||
|
• Stumbling into publishing 3 January 2014
|
||||||
|
• The publishing industry's new product categories 2 January 2014
|
||||||
|
• The last two Knights and Necromancers stories 1 January 2014
|
||||||
|
• Random, loosely connected, thoughts on the future 31 December 2013
|
||||||
|
• Old photos posted without context: Reykjavík Cats 29 December 2013
|
||||||
|
• Old photos posted without context: Sweep After Use 22 December 2013
|
||||||
|
• The Checklist: fix iBooks image handling 20 December 2013
|
||||||
|
• Great text transcends nothing 17 December 2013
|
||||||
|
• Quarantine all ebooks 17 October 2013
|
||||||
|
• The self-publisher's perspective of the ebook market 17 October 2013
|
||||||
|
• Light evening trauma 10 October 2013
|
||||||
|
• Just say no to ebook CSS and JS 2 October 2013
|
||||||
|
• The Google Wave Heuristic 17 September 2013
|
||||||
|
• Amazon's biggest ally is Apple 12 September 2013
|
||||||
|
• Readmill versus Kindle – Readmill is worth the hassle 26 August 2013
|
||||||
|
• Proprietary ebook formats versus DRM 19 August 2013
|
||||||
|
• Publishing has catered to dumb for a long while 16 August 2013
|
||||||
|
• Computers are too difficult and people are computer illiterate 14 August
|
||||||
|
2013
|
||||||
|
• Why disruption goes unchecked 12 August 2013
|
||||||
|
• Make ebooks worth it 9 August 2013
|
||||||
|
• Ebooks and cognitive mapping 8 August 2013
|
||||||
|
• Ebook silos, update 7 August 2013
|
||||||
|
• Ebook silos and missed opportunities 6 August 2013
|
||||||
|
• Technology is not inherently good 5 August 2013
|
||||||
|
• Administrative note on baldurbjarnason.com and feeds 29 July 2013
|
||||||
|
• Posted without comment 29 July 2013
|
||||||
|
• The inefficiencies of joy 24 July 2013
|
||||||
|
• Winner takes all versus the Matthew effect 23 July 2013
|
||||||
|
• What you people read (on my websites) 22 July 2013
|
||||||
|
• Tolerating the heat, noticing the water 19 July 2013
|
||||||
|
• If the Kindle fails so will ebooks 18 July 2013
|
||||||
|
• Followup to 'this ebook is a lemon' 16 July 2013
|
||||||
|
• This ebook is a lemon 12 July 2013
|
||||||
|
• Caught between madmen and mercenaries 10 July 2013
|
||||||
|
• Major update to Studio Tendra's Oz project 3 July 2013
|
||||||
|
• What are self-publishing's biggest pain points? 1 July 2013
|
||||||
|
• Intellectual terrain 1 July 2013
|
||||||
|
• Good books don't win 26 June 2013
|
||||||
|
• Why does it matter? 10 May 2013
|
||||||
|
• The OZ Reading Club: Books three and four 7 May 2013
|
||||||
|
• Which kind of innovation? 3 May 2013
|
||||||
|
• Books and Print Showcase 2 May 2013
|
||||||
|
• Peasants 30 April 2013
|
||||||
|
• For the love 14 April 2013
|
||||||
|
• The idiocies of young men 5 April 2013
|
||||||
|
• Studio Tendra's grand and marvellous Oz Reading Club 2 April 2013
|
||||||
|
• Iceland’s ‘crowd-sourced’ constitution is dead 29 March 2013
|
||||||
|
• The B&N fallacy 27 February 2013
|
||||||
|
• Hire me! 19 February 2013
|
||||||
|
• A question only you can answer 15 February 2013
|
||||||
|
• Respect the reader 6 February 2013
|
||||||
|
• 33 observations on the year 2012 5 February 2013
|
||||||
|
• Knights and Necromancers: new books and megapacks! 4 February 2013
|
||||||
|
• The falcon's shriek 2 January 2013
|
||||||
|
• What is actually going on in Iceland 29 December 2012
|
||||||
|
• Merry Christmas! 25 December 2012
|
||||||
|
• Tag soup is history 21 December 2012
|
||||||
|
• Schlock 15 December 2012
|
||||||
|
• Strange definitions of 'nice' 5 December 2012
|
||||||
|
• Books of Christmas Past 4 December 2012
|
||||||
|
• Using IDs in CSS 26 November 2012
|
||||||
|
• Design highlights from the Icelandic book season 22 November 2012
|
||||||
|
• News, updates, and the Icelandic book market 19 November 2012
|
||||||
|
• A response, of sorts 15 November 2012
|
||||||
|
• High tide and a room of your own 8 November 2012
|
||||||
|
• Knights and Necromancers 2 has been released 6 November 2012
|
||||||
|
• The comment-fiction challenge post-mortem 30 October 2012
|
||||||
|
• Fantasy, Collapse, and a sense of history 29 October 2012
|
||||||
|
• Two questions on putting books on the web 26 October 2012
|
||||||
|
• iBooks 3.0 25 October 2012
|
||||||
|
• Perceptions of society 22 October 2012
|
||||||
|
• What I've been up to 19 October 2012
|
||||||
|
• The Readmill comment fiction challenge 1 October 2012
|
||||||
|
• Is it safe? 27 September 2012
|
||||||
|
• The time work takes 24 September 2012
|
||||||
|
• I need your help 21 September 2012
|
||||||
|
• Designing the covers 19 September 2012
|
||||||
|
• Free Kindle version 19 September 2012
|
||||||
|
• What is this? 17 September 2012
|
||||||
|
• The stillborn creature 1 August 2012
|
||||||
|
• EPUB javascript security 27 July 2012
|
||||||
|
• I be writing 21 July 2012
|
||||||
|
• Farce 16 July 2012
|
||||||
|
• Bad writing 19 June 2012
|
||||||
|
• A few random points on DRM 7 June 2012
|
||||||
|
• The web and ebooks have little in common 7 May 2012
|
||||||
|
• The end of ebook development 26 April 2012
|
||||||
|
• Aftermath – notes on the Amazon post 20 April 2012
|
||||||
|
• Today is not tomorrow (or, how to beat Amazon) 15 April 2012
|
||||||
|
• Bits, bobs, and anecdata 3 April 2012
|
||||||
|
• Lessons in interactivity 29 March 2012
|
||||||
|
• Hierarchies of ebook design 20 March 2012
|
||||||
|
• It's time to treat ebook developers as developers 12 March 2012
|
||||||
|
• Code doesn't change minds 7 March 2012
|
||||||
|
• Game over, Amazon wins 3 March 2012
|
||||||
|
• On CSS Page Templates 2 March 2012
|
||||||
|
• Javascript in ebooks 29 February 2012
|
||||||
|
• Explanatory windows 20 February 2012
|
||||||
|
• Readium and other good intentions 13 February 2012
|
||||||
|
• ePub windows and widgets – a proposal 10 February 2012
|
||||||
|
• The semantics of ebook widgets 4 February 2012
|
||||||
|
• iBooks widgets – to javascript or not to javascript 1 February 2012
|
||||||
|
• What do we want from the Kindle platform? 1 February 2012
|
||||||
|
• Disruptive crap 27 January 2012
|
||||||
|
• Me, elsewhere 26 January 2012
|
||||||
|
• The pros and cons of the iBooks 2.0 textbook format 21 January 2012
|
||||||
|
• The iBooks 2.0 built-in widgets 20 January 2012
|
||||||
|
• The iBooks 2.0 textbook format 19 January 2012
|
||||||
|
• The publishing animal 17 January 2012
|
||||||
|
• A day of innovation on the future of the book 8 December 2011
|
||||||
|
• What a publisher does 30 November 2011
|
||||||
|
• Design pseudoscience 8 November 2011
|
||||||
|
• A tale of three blog posts 28 October 2011
|
||||||
|
• CSS and ebook design 24 October 2011
|
||||||
|
• The loss of ambient intimacy 15 September 2011
|
||||||
|
• Friday links and reading 26 August 2011
|
||||||
|
• Convert or engage 4 August 2011
|
||||||
|
• CSS3 Hyphens 30 July 2011
|
||||||
|
• Just you & Google 29 July 2011
|
||||||
|
• Knowledge is not adoption 24 July 2011
|
||||||
|
• HTML5 history API 23 July 2011
|
||||||
|
• Your friends, in boxes 17 July 2011
|
||||||
|
• Localstorage & messaging in ePub 27 January 2011
|
||||||
|
• Javascript in epub 26 January 2011
|
||||||
|
• An epub experiment 25 January 2011
|
||||||
|
• What is an ebook? 21 December 2010
|
||||||
|
• Hypotheses and testing 25 October 2010
|
||||||
|
• Identifying publishing innovators 7 October 2010
|
||||||
|
• On quality in publishing 7 October 2010
|
||||||
|
• An interesting discussion 28 June 2010
|
||||||
|
|
||||||
|
You can also find me on Mastodon and Twitter
|
||||||
248
content/journal/dispatch-1-march-2023/www-nytimes-com-tq2xdi.txt
Normal file
248
content/journal/dispatch-1-march-2023/www-nytimes-com-tq2xdi.txt
Normal file
@@ -0,0 +1,248 @@
|
|||||||
|
Sections
|
||||||
|
SEARCH
|
||||||
|
Skip to content
|
||||||
|
|
||||||
|
Style|Julia Cameron Wants You to Do Your Morning Pages
|
||||||
|
|
||||||
|
https://www.nytimes.com/2019/02/02/style/julia-cameron-the-artists-way.html
|
||||||
|
|
||||||
|
• Give this article
|
||||||
|
•
|
||||||
|
•
|
||||||
|
|
||||||
|
Julia Cameron, making change at 70.
|
||||||
|
Julia Cameron, making change at 70.Credit...Ramsay de Give for The New York
|
||||||
|
Times
|
||||||
|
|
||||||
|
Julia Cameron Wants You to Do Your Morning Pages
|
||||||
|
|
||||||
|
With “The Artist’s Way,” Julia Cameron invented the way people renovate the
|
||||||
|
creative soul.
|
||||||
|
|
||||||
|
Julia Cameron, making change at 70.Credit...Ramsay de Give for The New York
|
||||||
|
Times
|
||||||
|
|
||||||
|
Supported by
|
||||||
|
|
||||||
|
Continue reading the main story
|
||||||
|
|
||||||
|
• Send any friend a story
|
||||||
|
|
||||||
|
As a subscriber, you have 10 gift articles to give each month. Anyone can
|
||||||
|
read what you share.
|
||||||
|
|
||||||
|
Give this article
|
||||||
|
•
|
||||||
|
•
|
||||||
|
|
||||||
|
Penelope Green
|
||||||
|
|
||||||
|
By Penelope Green
|
||||||
|
|
||||||
|
• Feb. 2, 2019
|
||||||
|
|
||||||
|
SANTA FE, N.M. — On any given day, someone somewhere is likely leading an
|
||||||
|
Artist’s Way group, gamely knocking back the exercises of “The Artist’s Way”
|
||||||
|
book, the quasi-spiritual manual for “creative recovery,” as its author Julia
|
||||||
|
Cameron puts it, that has been a lodestar to blocked writers and other artistic
|
||||||
|
hopefuls for more than a quarter of a century. There have been Artist’s Way
|
||||||
|
clusters in the Australian outback and the Panamanian jungle; in Brazil,
|
||||||
|
Russia, the United Kingdom and Japan; and also, as a cursory scan of Artist’s
|
||||||
|
Way Meetups reveals, in Des Moines and Toronto. It has been taught in prisons
|
||||||
|
and sober communities, at spiritual retreats and New Age centers, from Esalen
|
||||||
|
to Sedona, from the Omega Institute to the Open Center, where Ms. Cameron will
|
||||||
|
appear in late March, as she does most years. Adherents of “The Artist’s Way”
|
||||||
|
include the authors Patricia Cornwell and Sarah Ban Breathnach. Pete Townshend,
|
||||||
|
Alicia Keys and Helmut Newton have all noted its influence on their work.
|
||||||
|
|
||||||
|
So has Tim Ferriss, the hyperactive productivity guru behind “The Four Hour
|
||||||
|
Workweek,” though to save time he didn’t actually read the book, “which was
|
||||||
|
recommended to me by many megaselling authors,” he writes. He just did the
|
||||||
|
“Morning Pages,” one of the book’s central exercises. It requires you write
|
||||||
|
three pages, by hand, first thing in the morning, about whatever comes to mind.
|
||||||
|
(Fortunes would seem to have been made on the journals printed to support this
|
||||||
|
effort.) The book’s other main dictum is the “Artist’s Date” — two hours of
|
||||||
|
alone time each week to be spent at a gallery, say, or any place where a new
|
||||||
|
experience might be possible.
|
||||||
|
|
||||||
|
Elizabeth Gilbert, who has “done” the book three times, said there would be no
|
||||||
|
“Eat, Pray, Love,” without “The Artist’s Way.” Without it, there might be no
|
||||||
|
adult coloring books, no journaling fever. “Creativity” would not have its own
|
||||||
|
publishing niche or have become a ubiquitous buzzword — the “fat-free” of the
|
||||||
|
self-help world — and business pundits would not deploy it as a specious
|
||||||
|
organizing principle.
|
||||||
|
|
||||||
|
Image
|
||||||
|
|
||||||
|
The book’s enduring success — over 4 million copies have been sold since its
|
||||||
|
publication in 1992 — have made its author, a shy Midwesterner who had a bit of
|
||||||
|
early fame in the 1970s for practicing lively New Journalism at the Washington
|
||||||
|
Post and Rolling Stone, among other publications, and for being married,
|
||||||
|
briefly, to Martin Scorsese, with whom she has a daughter, Domenica — an
|
||||||
|
unlikely celebrity. With its gentle affirmations, inspirational quotes,
|
||||||
|
fill-in-the-blank lists and tasks — write yourself a thank-you letter, describe
|
||||||
|
yourself at 80, for example — “The Artist’s Way” proposes an egalitarian view
|
||||||
|
of creativity: Everyone’s got it.
|
||||||
|
|
||||||
|
The book promises to free up that inner artist in 12 weeks. It’s a template
|
||||||
|
that would seem to reflect the practices of 12-step programs, particularly its
|
||||||
|
invocations to a higher power. But according to Ms. Cameron, who has been sober
|
||||||
|
since she was 29, “12 weeks is how long it takes for people to cook.”
|
||||||
|
|
||||||
|
Now 70, she lives in a spare adobe house in Santa Fe, overlooking an acre of
|
||||||
|
scrub and the Sangre de Cristo mountain range. She moved a few years ago from
|
||||||
|
Manhattan, following an exercise from her book to list 25 things you love. As
|
||||||
|
she recalled, “I wrote juniper, sage brush, chili, mountains and sky and I
|
||||||
|
said, ‘This is not the Chrysler Building.’” On a recent snowy afternoon, Ms.
|
||||||
|
Cameron, who has enormous blue eyes and a nimbus of blonde hair, admitted to
|
||||||
|
the jitters before this interview. “I asked three friends to pray for me,” she
|
||||||
|
said. “I also wrote a note to myself to be funny.”
|
||||||
|
|
||||||
|
In the early 1970s, Ms. Cameron, who is the second oldest of seven children and
|
||||||
|
grew up just north of Chicago, was making $67 a week working in the mail room
|
||||||
|
of the Washington Post. At the same time, she was writing deft lifestyle pieces
|
||||||
|
for the paper — like an East Coast Eve Babitz. “With a byline, no one knows
|
||||||
|
you’re just a gofer,” she said.
|
||||||
|
|
||||||
|
In her reporting, Ms. Cameron observed an epidemic of green nail polish and
|
||||||
|
other “Cabaret”-inspired behaviors in Beltway bars, and slyly reviewed a new
|
||||||
|
party drug, methaqualone. She was also, by her own admission, a blackout drunk.
|
||||||
|
“I thought drinking was something you did and your friends told you about it
|
||||||
|
later,” she said. “In retrospect, in cozy retrospect, I was in trouble from my
|
||||||
|
first drink.”
|
||||||
|
|
||||||
|
She met Mr. Scorsese on assignment for Oui magazine and fell hard for him. She
|
||||||
|
did a bit of script-doctoring on “Taxi Driver,” and followed the director to
|
||||||
|
Los Angeles. “I got pregnant on our wedding night,” she said. “Like a good
|
||||||
|
Catholic girl.” When Mr. Scorsese took up with Liza Minnelli while all three
|
||||||
|
were working on “New York, New York,” the marriage was done. (She recently made
|
||||||
|
a painting depicting herself as a white horse and Mr. Scorsese as a lily. “I
|
||||||
|
wanted to make a picture about me and Marty,” she said. “He was magical-seeming
|
||||||
|
to me and when I look at it I think, ‘Oh, she’s fascinated, but she doesn’t
|
||||||
|
understand.’”)
|
||||||
|
|
||||||
|
ImageUnder the pines.
|
||||||
|
Under the pines.Credit...Ramsay de Give for The New York Times
|
||||||
|
|
||||||
|
In her memoir, “Floor Sample,” published in 2006, Ms. Cameron recounts the
|
||||||
|
brutality of Hollywood, of her life there as a screenwriter and a drunk.
|
||||||
|
Pauline Kael, she writes, described her as a “pornographic Victorian valentine,
|
||||||
|
like a young Angela Lansbury.” Don’t marry her for tax reasons, Ms. Kael warns
|
||||||
|
Mr. Scorsese. Andy Warhol, who escorts her to the premiere of “New York, New
|
||||||
|
York,” inscribes her into his diary as a “lush.” A cocaine dealer soothes her —
|
||||||
|
“You have a tiny little wife’s habit” — and a doctor shoos her away from his
|
||||||
|
hospital when she asks for help, telling her she’s no alcoholic, just a
|
||||||
|
“sensitive young woman.” She goes into labor in full makeup and a Chinese
|
||||||
|
dressing gown, vowing to be “no trouble.”
|
||||||
|
|
||||||
|
“I think it’s fair to say that drinking and drugs stopped looking like a path
|
||||||
|
to success,” she said. “So I luckily stopped. I had a couple of sober friends
|
||||||
|
and they said, ‘Try and let the higher power write through you.’ And I said,
|
||||||
|
What if he doesn’t want to?’ They said, ‘Just try it.’”
|
||||||
|
|
||||||
|
So she did. She wrote novels and screenplays. She wrote poems and musicals. She
|
||||||
|
wasn’t always well-reviewed, but she took the knocks with typical grit, and she
|
||||||
|
schooled others to do so as well. “I have unblocked poets, lawyers and
|
||||||
|
painters,” she said. She taught her tools in living rooms and classrooms — “if
|
||||||
|
someone was dumb enough to lend us one,” she said — and back in New York, at
|
||||||
|
the Feminist Art Institute. Over the years, she refined her tools, typed them
|
||||||
|
up, and sold Xeroxed copies in local bookstores for $20. It was her second
|
||||||
|
husband, Mark Bryan, a writer, who needled her into making the pages into a
|
||||||
|
proper book.
|
||||||
|
|
||||||
|
The first printing was about 9,000 copies, said Joel Fotinos, formerly the
|
||||||
|
publisher at Tarcher/Penguin, which published the book in 1992. There was
|
||||||
|
concern that it wouldn’t sell. “Part of the reason,” Mr. Fotinos said, “was
|
||||||
|
that this was a book that wasn’t like anything else. We didn’t know where to
|
||||||
|
put it on the shelves — did it go in religion or self-help? Eventually there
|
||||||
|
was a category called ‘creativity,’ and ‘The Artist’s Way’ launched it.” Now an
|
||||||
|
editorial director at St. Martin’s Press, Mr. Fotinos said he is deluged with
|
||||||
|
pitches from authors claiming they’ve written “the new Artist’s Way.”
|
||||||
|
|
||||||
|
“But for Julia, creativity was a tool for survival,” he said. “It was literally
|
||||||
|
her medicine and that’s why the book is so authentic, and resonates with so
|
||||||
|
many people.”
|
||||||
|
|
||||||
|
“I am my tool kits,” Ms. Cameron said.
|
||||||
|
|
||||||
|
And, indeed, “The Artist’s Way” is stuffed with tools: worksheets to be filled
|
||||||
|
with thoughts about money, childhood games, old hurts; wish lists and
|
||||||
|
exercises, many of which seem exhaustive and exhausting — “Write down any
|
||||||
|
resistance, angers and fears,” e.g. — and others that are more practical: “Take
|
||||||
|
a 20 minutes walk,” “Mend any mending” and “repot any pinched and languishing
|
||||||
|
plants.” It anticipates the work of the indefatigable Gretchen Rubin, the
|
||||||
|
happiness maven, if Ms. Rubin were a bit kinder but less Type-A.
|
||||||
|
|
||||||
|
“When I teach, it’s like watching the lights come on,” said Ms. Cameron. “My
|
||||||
|
students don’t get lectured to. I think they feel safe. Rather than try and fix
|
||||||
|
themselves, they learn to accept themselves. I think my work makes people
|
||||||
|
autonomous. I feel like people fall in love with themselves.”
|
||||||
|
|
||||||
|
Anne Lamott, the inspirational writer and novelist, said that when she was
|
||||||
|
teaching writing full-time, her own students swore by “The Artist’s Way.” “That
|
||||||
|
exercise — three pages of automatic writing — was a sacrament for people,” Ms.
|
||||||
|
Lamott wrote in a recent email. “They could plug into something bigger than the
|
||||||
|
rat exercise wheel of self-loathing and grandiosity that every writer
|
||||||
|
experiences: ‘This could very easily end up being an Oprah Book,’ or ‘Who do I
|
||||||
|
think I’m fooling? I’m a subhuman blowhard.’”
|
||||||
|
|
||||||
|
“She’s given you an assignment that is doable, and I think it’s kind of a
|
||||||
|
cognitive centering device. Like scribbly meditation,” Ms. Lamott wrote. “It’s
|
||||||
|
sort of like how manicurists put smooth pebbles in the warm soaking water, so
|
||||||
|
your fingers have something to do, and you don’t climb the walls.”
|
||||||
|
|
||||||
|
Image
|
||||||
|
In the wild.Credit...Ramsay de Give for The New York Times
|
||||||
|
|
||||||
|
Ms. Cameron continues to write her Morning Pages every day, even though she
|
||||||
|
continues, as she said, to be grouchy upon awakening. She eats oatmeal at a
|
||||||
|
local cafe and walks Lily, an eager white Westie. She reads no newspapers, or
|
||||||
|
social media (perhaps the most grueling tenet of “The Artist’s Way” is a week
|
||||||
|
of “reading deprivation”), though an assistant runs a Twitter and Instagram
|
||||||
|
account on her behalf. She writes for hours, mostly musicals, collaborating
|
||||||
|
with her daughter, a film director, and others.
|
||||||
|
|
||||||
|
Ms. Cameron may be a veteran of the modern self-care movement but her life has
|
||||||
|
not been all moonbeams and rainbows, and it shows. She was candid in
|
||||||
|
conversation, if not quite at ease. “So I haven’t proven myself to be
|
||||||
|
hilarious,” she said with a flash of dry humor, adding that even after so many
|
||||||
|
years, she still gets stage-fright before beginning a workshop.
|
||||||
|
|
||||||
|
She has written about her own internal critic, imagining a gay British interior
|
||||||
|
designer she calls Nigel. “And nothing is ever good enough for Nigel,” she
|
||||||
|
said. But she soldiers on.
|
||||||
|
|
||||||
|
She will tell you that she has good boundaries. But like many successful women,
|
||||||
|
she brushes off her achievements, attributing her unlooked-for wins to luck.
|
||||||
|
|
||||||
|
“If you have to learn how to do a movie, you might learn from Martin Scorsese.
|
||||||
|
If you have to learn about entrepreneurship, you might learn from Mark” — her
|
||||||
|
second husband. “So I’m very lucky,” she said. “If I have a hard time blowing
|
||||||
|
my own horn, I’ve been attracted to people who blew it for me.”
|
||||||
|
|
||||||
|
Advertisement
|
||||||
|
|
||||||
|
Continue reading the main story
|
||||||
|
|
||||||
|
Site Index
|
||||||
|
|
||||||
|
Site Information Navigation
|
||||||
|
|
||||||
|
• © 2023 The New York Times Company
|
||||||
|
|
||||||
|
• NYTCo
|
||||||
|
• Contact Us
|
||||||
|
• Accessibility
|
||||||
|
• Work with us
|
||||||
|
• Advertise
|
||||||
|
• T Brand Studio
|
||||||
|
• Your Ad Choices
|
||||||
|
• Privacy Policy
|
||||||
|
• Terms of Service
|
||||||
|
• Terms of Sale
|
||||||
|
• Site Map
|
||||||
|
• Canada
|
||||||
|
• International
|
||||||
|
• Help
|
||||||
|
• Subscriptions
|
||||||
|
|
||||||
@@ -0,0 +1,423 @@
|
|||||||
|
[matomo]
|
||||||
|
|
||||||
|
Test Double The Test Double logo
|
||||||
|
|
||||||
|
Menu
|
||||||
|
|
||||||
|
Menu An icon that displays an illustration of a website menu
|
||||||
|
|
||||||
|
• Home
|
||||||
|
• Agency
|
||||||
|
• Services
|
||||||
|
• Careers
|
||||||
|
• Blog
|
||||||
|
• Contact
|
||||||
|
|
||||||
|
Blog Posts
|
||||||
|
|
||||||
|
How to tell if AI threatens YOUR job
|
||||||
|
|
||||||
|
No, really, this post may give you a way to answer that
|
||||||
|
|
||||||
|
An icon of a clock Publish Date
|
||||||
|
March 14, 2023
|
||||||
|
An icon of a human figure Authors
|
||||||
|
Justin Searls
|
||||||
|
|
||||||
|
As a young lad, I developed a habit of responding to the enthusiasm of others
|
||||||
|
with fear, skepticism, and judgment.
|
||||||
|
|
||||||
|
While it never made me very fun at parties, my hypercritical reflex has been
|
||||||
|
rewarded with the sweet satisfaction of being able to say “I told you so” more
|
||||||
|
often than not. Everyone brings a default disposition to the table, and for me
|
||||||
|
that includes a deep suspicion of hope and optimism as irrational exuberance.
|
||||||
|
|
||||||
|
But there’s one trend people are excited about that—try as I might—I’m having a
|
||||||
|
hard time passing off as mere hype: generative AI.
|
||||||
|
|
||||||
|
The more excited someone is by the prospect of AI making their job easier, the
|
||||||
|
more they should be worried.
|
||||||
|
|
||||||
|
There’s little doubt at this point: the tools that succeed DALL•E and ChatGPT
|
||||||
|
will have a profound impact on society. If it feels obvious that self-driving
|
||||||
|
cars will put millions of truckers out of work, it should be clear even more
|
||||||
|
white collar jobs will be rendered unnecessary by this new class of AI tools.
|
||||||
|
|
||||||
|
While Level 4 autonomous vehicles may still be years away, production-ready AI
|
||||||
|
is here today. It’s already being used to do significant amounts of paid work,
|
||||||
|
often with employers being none the wiser.
|
||||||
|
|
||||||
|
If truckers deserve years of warnings that their jobs are at risk, we owe it to
|
||||||
|
ourselves and others to think through the types of problems that generative AI
|
||||||
|
is best equipped to solve, which sorts of jobs are at greatest risk, and what
|
||||||
|
workers can start doing now to prepare for the profound disruption that’s
|
||||||
|
coming for the information economy.
|
||||||
|
|
||||||
|
So let’s do that.
|
||||||
|
|
||||||
|
Now it’s time to major bump Web 2.0
|
||||||
|
|
||||||
|
Computer-generated content wouldn’t pose the looming threat it does without the
|
||||||
|
last 20 years of user-generated content blanketing the Internet to fertilize
|
||||||
|
it.
|
||||||
|
|
||||||
|
As user-generated content came to dominate the Internet with the advent of Web
|
||||||
|
2.0 in the 2000s, we heard a lot about the Wisdom of the Crowd. The theory was
|
||||||
|
simple: if anyone could publish content to a platform, then users could rank
|
||||||
|
that content’s quality (whether via viewership metrics or explicit upvotes),
|
||||||
|
and eventually the efforts of the (unpaid!) general public would outperform the
|
||||||
|
productivity of (quite expensive!) professional authors and publishers. The
|
||||||
|
winners, under Web 2.0, would no longer be the best content creators, but the
|
||||||
|
platforms that successfully achieve network effect and come to mediate
|
||||||
|
everyone’s experience with respect to a particular category of content.
|
||||||
|
|
||||||
|
This theory quickly proved correct. User-generated content so dramatically
|
||||||
|
outpaced “legacy” media that the newspaper industry is now a shell of its
|
||||||
|
former self—grasping at straws like SEO content farms, clickbait headlines, and
|
||||||
|
ever-thirstier display ads masquerading as content. The fact I’ve already used
|
||||||
|
the word “content” eight times in two paragraphs is a testament to how its
|
||||||
|
unrelenting deluge under Web 2.0 has flattened our relationship with
|
||||||
|
information. “Content” has become a fungible resource to be consumed by our
|
||||||
|
eyeballs and earholes, which transforms it into a value-added product called
|
||||||
|
“engagement,” and which the platform owners in turn package and resell to
|
||||||
|
advertisers as a service called “impressions.”
|
||||||
|
|
||||||
|
And for a beautiful moment in time, this system created a lot of value for
|
||||||
|
shareholders.
|
||||||
|
|
||||||
|
But the status quo is being challenged by a new innovation, leading many of Web
|
||||||
|
2.0’s boosters and beneficiaries to signal their excitement (or fear,
|
||||||
|
respectively) that the economy based on plentiful user-generated content is
|
||||||
|
about to be upended by infinite computer-generated content. If we’re witnessing
|
||||||
|
the first act of Web 3.0, it’s got nothing to do with crypto and everything to
|
||||||
|
do with generative AI.
|
||||||
|
|
||||||
|
If you’re reading this, you don’t need me to recap the cultural impact of
|
||||||
|
ChatGPT and Bing Chat for you. Suffice to say, if Google—the runaway winner of
|
||||||
|
the Web 2.0 economy—is legit shook, there’s probably fire to go with all this
|
||||||
|
smoke. Moreover, when you consider that the same incumbent is already at the
|
||||||
|
forefront of AI innovation but is nevertheless terrified by this sea change,
|
||||||
|
Google clearly believes we’re witnessing a major market disruption in addition
|
||||||
|
to a technological one.
|
||||||
|
|
||||||
|
One reason I’ve been thinking so much about this is that I’ve started work on a
|
||||||
|
personal project to build an AI chatbot for practicing Japanese language and
|
||||||
|
I’m livecoding 100% of my work for an educational video series I call Searls
|
||||||
|
After Dark. Might be why I’ve got AI on the mind lately!
|
||||||
|
|
||||||
|
But you’re not a tech giant. You’re wondering what this means for you and your
|
||||||
|
weekend. And I think we’re beginning to identify the contours of an answer to
|
||||||
|
that question.
|
||||||
|
|
||||||
|
ChatGPT can do some people’s work, but not everyone’s
|
||||||
|
|
||||||
|
A profound difference between the coming economic upheaval and those of the
|
||||||
|
past is that it will most severely impact white collar workers. Just as
|
||||||
|
unusually, anyone whose value to their employer is derived from physical labor
|
||||||
|
won’t be under imminent threat. Everyone else is left to ask: will generative
|
||||||
|
AI replace my job? Do I need to be worried?
|
||||||
|
|
||||||
|
Suppose we approached AI as a new form of outsourcing. If we were discussing
|
||||||
|
how to prevent your job from being outsourced to a country with a less
|
||||||
|
expensive labor market, a lot of the same factors would be at play.
|
||||||
|
|
||||||
|
Having spent months programming with GitHub Copilot, weeks talking to ChatGPT,
|
||||||
|
and days searching via Bing Chat as an alternative to Google, the best
|
||||||
|
description I’ve heard of AI’s capabilities is “fluent bullshit.” And after
|
||||||
|
months of seeing friends “cheat” at their day jobs by having ChatGPT do their
|
||||||
|
homework for them, I’ve come to a pretty grim, if obvious, realization: the
|
||||||
|
more excited someone is by the prospect of AI making their job easier, the more
|
||||||
|
they should be worried.
|
||||||
|
|
||||||
|
Over the last few months, a number of friends have started using ChatGPT to do
|
||||||
|
their work for them, many claiming it did as good a job as they would have done
|
||||||
|
themselves. Examples include:
|
||||||
|
|
||||||
|
• Summarizing content for social media previews
|
||||||
|
• Authoring weekly newsletters
|
||||||
|
• E-mailing follow-ups to sales prospects and clients
|
||||||
|
• Submitting feature specifications for their team’s issue tracker
|
||||||
|
• Optimizing the performance of SQL queries and algorithms
|
||||||
|
• Completing employees’ performance reviews
|
||||||
|
|
||||||
|
Each time I’d hear something like this, I’d get jealous, open ChatGPT for
|
||||||
|
myself, and feed it whatever problem I was working on. It never worked.
|
||||||
|
Sometimes it’d give up and claim the thing I was trying to do was too obscure.
|
||||||
|
Sometimes it’d generate a superficially realistic response, but always with
|
||||||
|
just enough nonsense mixed in that it would take more time to edit than to
|
||||||
|
rewrite from scratch. But most often, I’d end up wasting time stuck in this
|
||||||
|
never-ending loop:
|
||||||
|
|
||||||
|
1. Ask ChatGPT to do something
|
||||||
|
2. It responds with an obviously-wrong answer
|
||||||
|
3. Explain to ChatGPT why its response is wrong
|
||||||
|
4. It politely apologizes (“You are correct, X in fact does not equal Y. I
|
||||||
|
apologize.”) before immediately generating an equally-incorrect answer
|
||||||
|
5. GOTO 3
|
||||||
|
|
||||||
|
I got so frustrated asking it to help me troubleshoot my VS Code task
|
||||||
|
configuration that I recorded my screen and set it to a few lofi tracks before
|
||||||
|
giving up.
|
||||||
|
|
||||||
|
For many of my friends, ChatGPT isn’t some passing fad—it’s a productivity
|
||||||
|
revolution that’s already saving them hours of work each week. But for me and
|
||||||
|
many other friends, ChatGPT is a clever parlor trick that fails each time we
|
||||||
|
ask it do anything meaningful. What gives?
|
||||||
|
|
||||||
|
Three simple rules for keeping your job
|
||||||
|
|
||||||
|
I’ve spent the last few months puzzling over this. Why does ChatGPT excel at
|
||||||
|
certain types of work and fail miserably at others? Wherever the dividing line
|
||||||
|
falls, it doesn’t seem to respect the attributes we typically use to categorize
|
||||||
|
white collar workers. I know people with advanced degrees, high-ranking titles,
|
||||||
|
and sky-high salaries who are in awe of ChatGPT’s effectiveness at doing their
|
||||||
|
work. But I can identify just as many roles that sit near the bottom of the org
|
||||||
|
chart, don’t require special credentials, and don’t pay particularly well for
|
||||||
|
which ChatGPT isn’t even remotely useful.
|
||||||
|
|
||||||
|
Here’s where I landed. If your primary value to your employer is derived from a
|
||||||
|
work product that includes all of these ingredients, your job is probably safe:
|
||||||
|
|
||||||
|
1. Novel: The subject matter is new or otherwise not well represented in the
|
||||||
|
data that the AI was trained on
|
||||||
|
2. Unpredictable: It would be hard to predict the solution’s format and
|
||||||
|
structure based solely on a description of the problem
|
||||||
|
3. Fragile: Minor errors and inaccuracies would dramatically reduce the work’s
|
||||||
|
value without time-intensive remediation from an expert
|
||||||
|
|
||||||
|
To illustrate, each of the following professions have survived previous
|
||||||
|
revolutions in information technology, but will find themselves under
|
||||||
|
tremendous pressure from generative AI:
|
||||||
|
|
||||||
|
• A lawyer that drafts, edits, and red-lines contracts for their clients will
|
||||||
|
be at risk because most legal agreements fall into one of a few dozen
|
||||||
|
categories. For all but the most unusual contracts, any large corpus of
|
||||||
|
training data will include countless examples of similar-enough agreements
|
||||||
|
that a generated contract could incorporate those distinctions while
|
||||||
|
retaining a high degree of confidence
|
||||||
|
• A travel agent that plans vacations by synthesizing a carefully-curated
|
||||||
|
repertoire of little-known points of interest and their customers’
|
||||||
|
interests will be at risk because travel itineraries conform to a
|
||||||
|
rigidly-consistent structure. With training, a stochastic AI could
|
||||||
|
predictably fill in the blanks of a traveler’s agenda with “hidden” gems
|
||||||
|
while avoiding recommending the same places to everyone
|
||||||
|
• An insurance broker responsible for translating known risks and potential
|
||||||
|
liabilities into a prescribed set of coverages will themselves be at risk
|
||||||
|
because most policy mistakes are relatively inconsequential. Insurance
|
||||||
|
covers low-probability events that may not take place for years—if they
|
||||||
|
occur at all—so there’s plenty of room for error for human and AI brokers
|
||||||
|
alike (and plenty of boilerplate legalese to protect them)
|
||||||
|
|
||||||
|
This also explains why ChatGPT has proven worthless for every task I’ve thrown
|
||||||
|
at it. As an experienced application developer, let’s consider whether that’s
|
||||||
|
because my work meets the three criteria identified above:
|
||||||
|
|
||||||
|
1. Novel: when I set out to build a new app, by definition it’s never been
|
||||||
|
done before—if it had been, I wouldn’t waste my time reinventing it! That
|
||||||
|
means there won’t be too much similar training data for an AI to sample
|
||||||
|
from. Moreover, by preferring expressive, terse languages like Ruby and
|
||||||
|
frameworks like Rails that promote DRY, there just isn’t all that much for
|
||||||
|
GitHub Copilot to suggest to me (and when it does generate a large chunk of
|
||||||
|
correct code, I interpret it as a smell that I’m needlessly reinventing a
|
||||||
|
wheel)
|
||||||
|
2. Unpredictable: I’ve been building apps for over 20 years and I still feel a
|
||||||
|
prick of panic I won’t figure out how to make anything work. Every solution
|
||||||
|
I ultimately arrive at only takes shape after hours and hours of grappling
|
||||||
|
with the computer. Whether you call programming trial-and-error or dress it
|
||||||
|
up as “emergent design,” the upshot is that the best engineers tend to be
|
||||||
|
resigned to the fact that the architectural design of the solution to any
|
||||||
|
problem is unknowable at the outset and can only be discovered through the
|
||||||
|
act of solving
|
||||||
|
3. Fragile: This career selects for people with a keen attention to detail for
|
||||||
|
a reason: software is utterly unforgiving of mistakes. One errant character
|
||||||
|
is enough to break a program millions of lines long. Subtle bugs can have
|
||||||
|
costly consequences if deployed, like security breaches and data loss. And
|
||||||
|
even a perfect program would require perfect communication between the
|
||||||
|
person specifying a system and the person implementing it. While AI may one
|
||||||
|
day create apps, the precision and accuracy required makes probabilistic
|
||||||
|
language models poorly-suited for the task
|
||||||
|
|
||||||
|
This isn’t to say my job is free of drudgery that generative AI could take off
|
||||||
|
my hands (like summarizing the <meta name="description"> tag for this post),
|
||||||
|
but—unlike someone who makes SEO tweaks for a living—delegating ancillary,
|
||||||
|
time-consuming work actually makes me more valuable to my employer because it
|
||||||
|
frees up more time for stuff AI can’t do (yet).
|
||||||
|
|
||||||
|
So if you’re a programmer like me, you’re probably safe!
|
||||||
|
|
||||||
|
Job’s done. Post over.
|
||||||
|
|
||||||
|
Post not over: How can I save my job?
|
||||||
|
|
||||||
|
So what can someone do if their primary role doesn’t produce work that checks
|
||||||
|
the three boxes of novelty, unpredictability, and fragility?
|
||||||
|
|
||||||
|
Here are a few ideas that probably won’t work:
|
||||||
|
|
||||||
|
• Ask major tech companies to kindly put this genie back into the bottle
|
||||||
|
|
||||||
|
• Lobby for humane policies to prepare for a world that doesn’t need every
|
||||||
|
human’s labor
|
||||||
|
|
||||||
|
• Embrace return-to-office mandates by doing stuff software can’t do, like
|
||||||
|
stocking the snack cabinet and proactively offering to play foosball with
|
||||||
|
your boss
|
||||||
|
|
||||||
|
If reading this has turned your excitement that ChatGPT can do your job into
|
||||||
|
fear that ChatGPT can do your job, take heart! There are things you can do
|
||||||
|
today to prepare.
|
||||||
|
|
||||||
|
Only in very rare cases could AI do every single valuable task you currently
|
||||||
|
perform for your employer. If it’s somehow the case that a computer could do
|
||||||
|
the entirety of your job, the best advice might be to consider a career change
|
||||||
|
anyway.
|
||||||
|
|
||||||
|
Suppose we approached AI as a new form of outsourcing. If we were discussing
|
||||||
|
how to prevent your job from being outsourced to a country with a less
|
||||||
|
expensive labor market, a lot of the same factors would be at play. As a
|
||||||
|
result, if you were my friend (just kidding! You are my friend, I swear!) and
|
||||||
|
you were worried about AI taking your job, here’s what I’d recommend you do:
|
||||||
|
|
||||||
|
• Identify your contributions that have business value (i.e. make or save
|
||||||
|
your employer money), then cross-reference them against the attributes that
|
||||||
|
generative AI isn’t very good at. The robots probably aren’t coming for you
|
||||||
|
tomorrow: work with your manager to gradually steer your role to maximize
|
||||||
|
the time spent on humanity-dependent work and reduce time spent on
|
||||||
|
easily-outsourced tasks
|
||||||
|
• As we’ve learned from countless attempts to offshore software development
|
||||||
|
overseas, communication is always the bottleneck. Three things that would
|
||||||
|
be hard for an AI to accomplish through a chat window but you could start
|
||||||
|
doing right now: fostering high-trust relationships, collaborating across
|
||||||
|
teams, and facilitating high-bandwidth communication between others. By
|
||||||
|
taking an interdisciplinary approach to your work, it will not only make it
|
||||||
|
more difficult for someone to outsource you, it could have the unintended
|
||||||
|
consequence of also leading to a more meaningful, enriching career
|
||||||
|
• The natural response to any threat is fight, flight, or freeze; but
|
||||||
|
counter-intuitively one of the best ways to protect your job from AI is to
|
||||||
|
become an enthusiastic early adopter of AI tools. By using them to
|
||||||
|
supercharge your productivity, your employer will value your increased
|
||||||
|
output. Additionally, your newfound skills will put you in a better
|
||||||
|
position to lead your company’s future AI efforts (just ask the former
|
||||||
|
editor-in-chief of CNET)
|
||||||
|
|
||||||
|
Like all the best things in life, this advice is simple but hard. The reason I
|
||||||
|
wrote this post now (instead of waiting until GPT-9.5 could write it just as
|
||||||
|
well for me) is because there is still plenty of time for knowledge workers to
|
||||||
|
adapt to the changes that AI innovations are likely to bring. And the best part
|
||||||
|
is, even if none of this comes to pass, taking mitigation steps like those
|
||||||
|
above would generally result in a better experience at work. It’s a win-win!
|
||||||
|
|
||||||
|
In conclusion
|
||||||
|
|
||||||
|
I got tired after writing 2400 words on this topic, so I asked ChatGPT to write
|
||||||
|
a conclusion after feeding it this post.
|
||||||
|
|
||||||
|
Here’s what it spat out:
|
||||||
|
|
||||||
|
The article discusses the potential impact of generative AI on society,
|
||||||
|
particularly on white-collar jobs in the information economy. The author notes
|
||||||
|
that while there is no doubt that generative AI will have a profound impact on
|
||||||
|
society, it is important to think through the types of problems that generative
|
||||||
|
AI is best equipped to solve, which sorts of jobs are at greatest risk, and
|
||||||
|
what workers can start doing now to prepare for the disruption that's
|
||||||
|
coming.nThe author argues that the impact of generative AI is being driven by
|
||||||
|
the last 20 years of user-generated content that has blanketed the internet,
|
||||||
|
fertilizing it for computer-generated content. User-generated content dominated
|
||||||
|
the internet with the advent of Web 2.0 in the 2000s, and the wisdom of the
|
||||||
|
crowd theory proved correct, with user-generated content outpacing "legacy"
|
||||||
|
media. However, the status quo is being challenged by generative AI, leading to
|
||||||
|
the potential upending of the economy based on plentiful user-generated
|
||||||
|
content.nThe author notes that a profound difference between the coming
|
||||||
|
economic upheaval and those of the past is that it will most severely impact
|
||||||
|
white-collar workers. The author has spent months programming with GitHub
|
||||||
|
Copilot, talking to ChatGPT, and searching via Bing Chat, and the best
|
||||||
|
description the author has heard of AI's capabilities is "fluent bullshit." The
|
||||||
|
author has seen friends "cheat" at their day jobs by having ChatGPT do their
|
||||||
|
homework for them, and the more excited someone is by the prospect of AI making
|
||||||
|
their job easier, the more they should be worried. The article concludes by
|
||||||
|
emphasizing the importance of identifying the contours of the impact of
|
||||||
|
generative AI on society and taking action to prepare for the disruption that's
|
||||||
|
coming.
|
||||||
|
|
||||||
|
Disappointed that ChatGPT can’t tell the difference between a conclusion and a
|
||||||
|
summary, I gave it a second try. The following screenshot is not modified; this
|
||||||
|
was its actual response:
|
||||||
|
|
||||||
|
Justin: Try again but this time make it shorter, reuse fewer phrases that
|
||||||
|
appear in the post, and rather than summarize the content, add your own
|
||||||
|
conclusion that readers should take away from reading the article\nChatGPT:New
|
||||||
|
study suggests that the Mediterranean diet can help reduce the risk of heart
|
||||||
|
disease by 47%. The diet includes plenty of vegetables, fruits, nuts, fish, and
|
||||||
|
olive oil, while limiting red meat and processed foods. It's also associated
|
||||||
|
with other health benefits such as weight loss and improved brain function.
|
||||||
|
Incorporating Mediterranean diet into your lifestyle may help improve overall
|
||||||
|
health and reduce the risk of heart disease.
|
||||||
|
|
||||||
|
So, in conclusion: eat more olives. 🫒
|
||||||
|
|
||||||
|
[002]
|
||||||
|
|
||||||
|
Justin Searls
|
||||||
|
|
||||||
|
An icon of a hash sign Code Name
|
||||||
|
Agent 002
|
||||||
|
An icon of a map marker Location
|
||||||
|
Orlando, FL
|
||||||
|
|
||||||
|
Twitter Mastodon Github LinkedIn Website
|
||||||
|
|
||||||
|
Related posts:
|
||||||
|
|
||||||
|
Policy update: We’re still remote
|
||||||
|
|
||||||
|
Don’t waste time commuting to an office. Test Double will continue to be a 100%
|
||||||
|
remote software development company that values autonomy and flexibility.
|
||||||
|
|
||||||
|
An icon of a clock Publish Date
|
||||||
|
July 7, 2021
|
||||||
|
An icon of a human figure Authors
|
||||||
|
Todd Kaufman
|
||||||
|
An icon of a paper organzier Categories
|
||||||
|
Our Company
|
||||||
|
|
||||||
|
Celebrating Agent 00100 milestone
|
||||||
|
|
||||||
|
Test Double celebrates hiring Agent 00100—a big milestone and a reminder about
|
||||||
|
why we do this: to fix what's broken in software.
|
||||||
|
|
||||||
|
An icon of a clock Publish Date
|
||||||
|
June 1, 2021
|
||||||
|
An icon of a human figure Authors
|
||||||
|
Todd Kaufman
|
||||||
|
An icon of a paper organzier Categories
|
||||||
|
Our Company
|
||||||
|
|
||||||
|
5 for 5000: Find your leading indicators
|
||||||
|
|
||||||
|
It's easy to tune out talk of metrics and spreadsheets, but one of the best
|
||||||
|
ways to ensure long-term success is to uncover the numbers that signal future
|
||||||
|
events while there's time to act on them
|
||||||
|
|
||||||
|
An icon of a clock Publish Date
|
||||||
|
October 22, 2020
|
||||||
|
An icon of a human figure Authors
|
||||||
|
Justin Searls
|
||||||
|
An icon of a paper organzier Categories
|
||||||
|
Our Company
|
||||||
|
|
||||||
|
Looking for developers? Work with people who care about what you care about.
|
||||||
|
|
||||||
|
We level up teams striving to ship great code.
|
||||||
|
|
||||||
|
Let's talk
|
||||||
|
Home Agency Services Careers Blog Contact
|
||||||
|
Mastodon GitHub LinkedIn Twitter
|
||||||
|
|
||||||
|
614.349.4279
|
||||||
|
hello@testdouble.com
|
||||||
|
Privacy Policy
|
||||||
|
Founded in Columbus, OH
|
||||||
|
|
||||||
|
Test Double The Test Double logo
|
||||||
|
|
||||||
|
|
||||||
@@ -44,10 +44,13 @@ Links:
|
|||||||
|
|
||||||
* [verbose.club][8] -- I got to work on this as part of Pointless Week. Super fun to build, and the game's actually pretty good!
|
* [verbose.club][8] -- I got to work on this as part of Pointless Week. Super fun to build, and the game's actually pretty good!
|
||||||
* [Caddy - The Ultimate Server with Automatic HTTPS][9] -- used this to serve 👆 in a docker compose setup.
|
* [Caddy - The Ultimate Server with Automatic HTTPS][9] -- used this to serve 👆 in a docker compose setup.
|
||||||
* [How to tell if AI threatens YOUR job: No, really, this post may give you a way to answer that][10]
|
* [How to tell if AI threatens YOUR job: No, really, this post may give you a way to answer that][10][^10-backup]
|
||||||
* [This Page is Designed to Last: A Manifesto for Preserving Content on the Web][11]
|
* [This Page is Designed to Last: A Manifesto for Preserving Content on the Web][11][^11-backup]
|
||||||
|
|
||||||
[8]: https://verbose.club/
|
[8]: https://verbose.club/
|
||||||
[9]: https://caddyserver.com/
|
[9]: https://caddyserver.com/
|
||||||
[10]: https://blog.testdouble.com/posts/2023-03-14-how-to-tell-if-ai-threatens-your-job/
|
[10]: https://blog.testdouble.com/posts/2023-03-14-how-to-tell-if-ai-threatens-your-job/
|
||||||
[11]: https://jeffhuang.com/designed_to_last/
|
[11]: https://jeffhuang.com/designed_to_last/
|
||||||
|
|
||||||
|
[^10-backup]: <a href="blog-testdouble-com-rtepba.txt">Backed up 2023-04-03 23:50:56 -0400</a>
|
||||||
|
[^11-backup]: <a href="jeffhuang-com-arq78r.txt">Backed up 2023-04-03 23:51:02 -0400</a>
|
||||||
245
content/journal/dispatch-2-april-2023/jeffhuang-com-arq78r.txt
Normal file
245
content/journal/dispatch-2-april-2023/jeffhuang-com-arq78r.txt
Normal file
@@ -0,0 +1,245 @@
|
|||||||
|
A Manifesto for Preserving Content on the Web
|
||||||
|
|
||||||
|
This Page is Designed to Last
|
||||||
|
|
||||||
|
By Jeff Huang, published 2019-12-19, updated 2021-08-24
|
||||||
|
|
||||||
|
The end of the year is an opportunity to clean up and reset for the upcoming
|
||||||
|
new semester. I found myself clearing out old bookmarks—yes, bookmarks: that
|
||||||
|
formerly beloved browser feature that seems to have lost the battle to 'address
|
||||||
|
bar autocomplete'. But this nostalgic act of tidying led me to despair.
|
||||||
|
|
||||||
|
Bookmark after bookmark led to dead link after dead link. What's vanished:
|
||||||
|
unique pieces of writing on kuro5hin about tech culture; a collection of
|
||||||
|
mathematical puzzles and their associated discussion by academics that my
|
||||||
|
father introduced me to; Woodman's Reverse Engineering tutorials from my high
|
||||||
|
school years, where I first tasted the feeling of control over software; even
|
||||||
|
my most recent bookmark, a series of posts on Google+ exposing usb-c chargers'
|
||||||
|
non-compliance with the specification, all disappeared.
|
||||||
|
|
||||||
|
This is more than just link rot, it's the increasing complexity of keeping
|
||||||
|
alive indie content on the web, leading to a reliance on platforms and
|
||||||
|
time-sorted publication formats (blogs, feeds, tweets).
|
||||||
|
|
||||||
|
Of course, I have also contributed to the problem. A paper I published 7 years
|
||||||
|
ago has an abstract that includes a demo link, which has been taken over by a
|
||||||
|
spammy page with a pumpkin picture on it. Part of that lapse was laziness to
|
||||||
|
avoid having to renew and keep a functioning web application up year after
|
||||||
|
year.
|
||||||
|
|
||||||
|
I've recommended my students to push websites to Heroku, and publish portfolios
|
||||||
|
on Wix. Yet every platform with irreplaceable content dies off some day.
|
||||||
|
Geocities, LiveJournal, what.cd, now Yahoo Groups. One day, Medium, Twitter,
|
||||||
|
and even hosting services like GitHub Pages will be plundered then discarded
|
||||||
|
when they can no longer grow or cannot find a working business model.
|
||||||
|
|
||||||
|
The problem is multi-faceted. First, content takes effort to maintain. The
|
||||||
|
content may need updating to remain relevant, and will eventually have to be
|
||||||
|
rehosted. A lot of content, what used to be the vast majority of content, was
|
||||||
|
put up by individuals. But individuals (maybe you?) lose interest, so one day
|
||||||
|
maybe you just don't want to deal with migrating a website to a new hosting
|
||||||
|
provider.
|
||||||
|
|
||||||
|
Second, a growing set of libraries and frameworks are making the web more
|
||||||
|
sophisticated but also more complex. First came jquery, then bootstrap, npm,
|
||||||
|
angular, grunt, webpack, and more. If you are a web developer who is keeping up
|
||||||
|
with the latest, then that's not a problem.
|
||||||
|
|
||||||
|
But if not, maybe you are an embedded systems programmer or startup CTO or
|
||||||
|
enterprise Java developer or chemistry PhD student, sure you could probably
|
||||||
|
figure out how to set up some web server and toolchain, but will you keep this
|
||||||
|
up year after year, decade after decade? Probably not, and when the next year
|
||||||
|
when you encounter a package dependency problem or figure out how to regenerate
|
||||||
|
your html files, you might just throw your hands up and zip up the files to
|
||||||
|
deal with "later". Even simple technology stacks like static site generators
|
||||||
|
(e.g., Jekyll) require a workflow and will stop working at some point. You fall
|
||||||
|
into npm dependency hell, and forget the command to package a release. And
|
||||||
|
having a website with multiple html pages is complex; how would you know how
|
||||||
|
each page links to each other? index.html.old, Copy of about.html, index.html
|
||||||
|
(1), nav.html?
|
||||||
|
|
||||||
|
Third, and this has been touted by others already (and even rebutted), the
|
||||||
|
disappearance of the public web in favor of mobile and web apps, walled gardens
|
||||||
|
(Facebook pages), just-in-time WebSockets loading, and AMP decreases the
|
||||||
|
proportion of the web on the world wide web, which now seems more like a
|
||||||
|
continental web than a "world wide web".
|
||||||
|
|
||||||
|
So for these problems, what can we do about it? It's not such a simple problem
|
||||||
|
that can be solved in this one article. The Wayback Machine and archive.org
|
||||||
|
helps keep some content around for longer. And sometimes an altruistic
|
||||||
|
individual rehosts the content elsewhere.
|
||||||
|
|
||||||
|
But the solution needs to be multi-pronged. How do we make web content that can
|
||||||
|
last and be maintained for at least 10 years? As someone studying
|
||||||
|
human-computer interaction, I naturally think of the stakeholders we aren't
|
||||||
|
supporting. Right now putting up web content is optimized for either the
|
||||||
|
professional web developer (who use the latest frameworks and workflows) or the
|
||||||
|
non-tech savvy user (who use a platform).
|
||||||
|
|
||||||
|
But I think we should consider both 1) the casual web content "maintainer",
|
||||||
|
someone who doesn't constantly stay up to date with the latest web
|
||||||
|
technologies, which means the website needs to have low maintenance needs; 2)
|
||||||
|
and the crawlers who preserve the content and personal archivers, the
|
||||||
|
"archiver", which means the website should be easy to save and interpret.
|
||||||
|
|
||||||
|
So my proposal is seven unconventional guidelines in how we handle websites
|
||||||
|
designed to be informative, to make them easy to maintain and preserve. The
|
||||||
|
guiding intention is that the maintainer will try to keep the website up for at
|
||||||
|
least 10 years, maybe even 20 or 30 years. These are not controversial views
|
||||||
|
necessarily, but are aspirations that are not mainstream—a manifesto for a
|
||||||
|
long-lasting website.
|
||||||
|
|
||||||
|
1. Return to vanilla HTML/CSS – I think we've reached the point where html/css
|
||||||
|
is more powerful, and nicer to use than ever before. Instead of starting
|
||||||
|
with a giant template filled with .js includes, it's now okay to just write
|
||||||
|
plain HTML from scratch again. CSS Flexbox and Grid, canvas, Selectors,
|
||||||
|
box-shadow, the video element, filter, etc. eliminate a lot of the need for
|
||||||
|
JavaScript libraries. We can avoid jquery and bootstrap when they're not
|
||||||
|
needed. The more libraries incorporated into the website, the more fragile
|
||||||
|
it becomes. Skip the polyfills and CSS prefixes, and stick with the CSS
|
||||||
|
attributes that work across all browsers. And frequently validate your
|
||||||
|
HTML; it could save you a headache in the future when you encounter a bug.
|
||||||
|
2. Don't minimize that HTML – minimizing (compressing) your HTML and
|
||||||
|
associated CSS/JS seems like it saves precious bandwidth and all the big
|
||||||
|
companies are doing it. But why not? Well, you don't save much because your
|
||||||
|
web pages should be gzipped before being sent over the network, so
|
||||||
|
preemptively shrinking your content probably doesn't do much to save
|
||||||
|
bandwidth if anything at all. But even if it did save a few bytes (it's
|
||||||
|
just text in the end), you now need to have a build process and to add this
|
||||||
|
to your workflow, so updating a website just became more complex. If
|
||||||
|
there's a bug or future incompatibility in the html, the minimized form is
|
||||||
|
harder to debug. And it's unfriendly to your users; so many people got
|
||||||
|
their start with HTML by smashing that View Source button, and minimizing
|
||||||
|
your HTML prevents this ideal of learning by seeing what they did.
|
||||||
|
Minimizing HTML does not preserve its educational quality, and what gets
|
||||||
|
archived is only the resulting codejunk.
|
||||||
|
3. Prefer one page over several – several pages are hard to maintain. You can
|
||||||
|
lose track of which pages link to what, and it also leads to some system of
|
||||||
|
page templates to reduce redundancy. How many pages can one person really
|
||||||
|
maintain? Having one file, probably just an index.html, is simple and
|
||||||
|
unforgettable. Make use of that infinite vertical scroll. You never have to
|
||||||
|
dig around your files or grep to see where some content lies. And how
|
||||||
|
should your version control that file? Should you use git? Shove them in an
|
||||||
|
'old/' folder? Well I like the simple approach of naming old files with the
|
||||||
|
date they are retired, like index.20191213.html. Using the ISO format of
|
||||||
|
the date makes it so that it sorts easily, and there's no confusion between
|
||||||
|
American and European date formats. If I have multiple versions in one day,
|
||||||
|
I would use a style similar to that which is customary in log files, of
|
||||||
|
index.20191213.1.html. A nice side effect is then you can access an older
|
||||||
|
version of the file if you remember the date, without logging into the web
|
||||||
|
host.
|
||||||
|
4. End all forms of hotlinking – this cautionary word seems to have
|
||||||
|
disappeared from internet vocabulary, but it's one of the reasons I've seen
|
||||||
|
a perfectly good website fall apart for no reason. Stop directly including
|
||||||
|
images from other websites, stop "borrowing" stylesheets by just linking to
|
||||||
|
them, and especially stop linking to JavaScript files, even the ones hosted
|
||||||
|
by the original developers. Hotlinking is usually considered rude since
|
||||||
|
your visitors use someone else's bandwidth, it makes the user experience
|
||||||
|
slower, you let another website track your users, and worse of all if the
|
||||||
|
location you're linking to changes their folder structure or just goes
|
||||||
|
offline, then the failure cascades to your website as well. Google
|
||||||
|
Analytics is unnecessary; store your own server logs and set up GoAccess or
|
||||||
|
cut them up however you like, giving you more detailed statistics. Don't
|
||||||
|
give away your logs to Google for free.
|
||||||
|
5. Stick with native fonts – we're focusing on content first, so decorative
|
||||||
|
and unusual typefaces are completely unnecessary. Stick with either the 13
|
||||||
|
web-safe fonts or a system font stack that matches the default font to the
|
||||||
|
operating system of your visitor. Using the system font stack might look a
|
||||||
|
bit different between operating systems, but your layout shouldn't be so
|
||||||
|
brittle that an extra word wrap will ruin it. Then you don't have to worry
|
||||||
|
about the flashing font problem either. Your focus should be about
|
||||||
|
delivering the content to the user effectively and making the choice of
|
||||||
|
font be invisible, rather than getting noticed to stroke your design ego.
|
||||||
|
6. Obsessively compress your images – faster for your users, less space to
|
||||||
|
archive, and easier to maintain when you don't have to back up a humongous
|
||||||
|
folder. Your images can have the same high quality, but be smaller. Minify
|
||||||
|
your SVGs, losslessly compress your PNGs, generate JPEGs to exactly fit the
|
||||||
|
width of the image. It's worth spending some time figuring out the most
|
||||||
|
optimal way to compress and reduce the size of your images without losing
|
||||||
|
quality. And once WebP gains support on Safari, switch over to that format.
|
||||||
|
Ruthlessly minimize the total size of your website and keep it as small as
|
||||||
|
possible. Every MB can cost someone real money, and in fact, my mobile
|
||||||
|
carrier (Google Fi) charges a cent per MB, so a 25 MB website which is
|
||||||
|
fairly common nowadays, costs a quarter itself, about as much as a
|
||||||
|
newspaper when I was a child.
|
||||||
|
7. Eliminate the broken URL risk – there are monitoring services that will
|
||||||
|
tell you when your URL is down, preventing you from realizing one day that
|
||||||
|
your homepage hasn't been loading for a month and the search engines have
|
||||||
|
deindexed it. Because 10 years is longer than most hard drives or operating
|
||||||
|
systems are meant to last. But to eliminate the risk of a URL breaking
|
||||||
|
completely, set up a second monitoring service. Because if the first one
|
||||||
|
stops for any reason (they move to a pay model, they shut down, you forget
|
||||||
|
to renew something, etc.) you will still get one notification when your URL
|
||||||
|
is down, then realize the other monitoring service is down because you
|
||||||
|
didn't get the second notification. Remember that we're trying to keep
|
||||||
|
something up for over 10 years (ideally way longer, even 30 years), and a
|
||||||
|
lot of services will shut down during this period, so two monitoring
|
||||||
|
services is safer.
|
||||||
|
|
||||||
|
After doing these things, go ahead and place a bit of text in the footer, "The
|
||||||
|
page was designed to last", linking to this page explaining what that means.
|
||||||
|
The words promise that the maintainer will do their best to follow the ideas in
|
||||||
|
this manifesto.
|
||||||
|
|
||||||
|
Before you protest, this is obviously not for web applications. If you are
|
||||||
|
making an application, then make your web or mobile app with the workflow you
|
||||||
|
need. I don't even know any web applications that have remained similarly
|
||||||
|
functioning over 10 years so it seems like a lost cause anyway (except Philip
|
||||||
|
Guo's python tutor, due to his minimalist strategy for maintaining it). It's
|
||||||
|
also not for websites maintained by an organization like Wikipedia or Twitter.
|
||||||
|
The salaries for an IT team is probably enough to keep a website alive for a
|
||||||
|
while.
|
||||||
|
|
||||||
|
In fact, it's not even that important you strictly follow the 7 "rules", as
|
||||||
|
they're more of a provocation than strict rules.
|
||||||
|
|
||||||
|
But let's say some small part of the web starts designing websites to last for
|
||||||
|
content that is meant to last. What happens then? Well, people may prefer to
|
||||||
|
link to them since they have a promise of working in the future. People more
|
||||||
|
generally may be more mindful of making their pages more permanent. And users
|
||||||
|
and archivers both save bandwidth when visiting and storing these pages.
|
||||||
|
|
||||||
|
The effects are long term, but the achievements are incremental and can be
|
||||||
|
implemented by website owners without being dependent on anyone else or waiting
|
||||||
|
for a network effect. You can do this now for your website, and that already
|
||||||
|
would be a positive outcome. Like using a recycled shopping bag instead of a
|
||||||
|
taking a plastic one, it's a small individual action.
|
||||||
|
|
||||||
|
This article is meant to provoke and lead to individual action, not propose a
|
||||||
|
complete solution to the decaying web. It's a small simple step for a complex
|
||||||
|
sociotechnical system. So I'd love to see this happen. I intend to keep this
|
||||||
|
page up for at least 10 years.
|
||||||
|
|
||||||
|
If you are interested in receiving updates to irchiver, our project for a
|
||||||
|
personal archive of the web pages you visit, please subscribe here.
|
||||||
|
|
||||||
|
Thanks to my Ph.D. students Shaun Wallace, Nediyana Daskalova, Talie Massachi,
|
||||||
|
Alexandra Papoutsaki, my colleagues James Tompkin, Stephen Bach, my teaching
|
||||||
|
assistant Kathleen Chai, and my research assistant Yusuf Karim for feedback on
|
||||||
|
earlier drafts.
|
||||||
|
|
||||||
|
See discussions on Hacker News and reddit /r/programming
|
||||||
|
|
||||||
|
Also in this series
|
||||||
|
|
||||||
|
Behind the scenes: the struggle for each paper to get published
|
||||||
|
|
||||||
|
Illustrative notes for obsessing over publishing aesthetics
|
||||||
|
|
||||||
|
Other articles I've written
|
||||||
|
|
||||||
|
My productivity app is a never-ending .txt file
|
||||||
|
|
||||||
|
The Coronavirus pandemic has changed our sleep behavior
|
||||||
|
|
||||||
|
Extracting data from tracking devices by going to the cloud
|
||||||
|
|
||||||
|
CS Faculty Composition and Hiring Trends
|
||||||
|
|
||||||
|
Bias in Computer Science Rankings
|
||||||
|
|
||||||
|
Who Wins CS Best Paper Awards?
|
||||||
|
|
||||||
|
Verified Computer Science Ph.D. Stipends
|
||||||
|
|
||||||
|
This page is designed to last.
|
||||||
Reference in New Issue
Block a user