Clearly that certificate only applies to their website, though, and not to e.g. their emails. When you sign up an account with them, you need to verify your email address. They send you
a (HTML-only) email with a link to click. Here’s what that link looks like to a sighted person:
So far, so good. But here’s the HTML code they’re using to create that button. Maybe you’ll spot
the problem:
Despite specifying the font to use three times, they don’t actually have any alt text. So for somebody who can’t see that image, the link is
completely unusable1.
This made me angry enough that I gave up on my transaction and bought my train tickets from LNER instead.
Accessibility matters. And that includes emails. Do better, Avanti.
Footnotes
1 Incidentally, this also makes the email unusable for privacy-conscious people who, like
me, don’t routinely load remote images in emails. But that’s a secondary concern, really.
The video below is presented in portrait orientation, because your screen is taller than it is wide.
The video below is presented in landscape orientation, because your screen is wider than it is tall.
The video below is presented in square orientation (the Secret Bonus Square Video!), because your screen has approximately the same width as as its height. Cool!
This is possible (with a single <video> element, and without any Javascript!) thanks to some cool HTML features you might not be aware of, which I’ll briefly explain
in the video. Or scroll down for the full details.
<videocontrols><sourcesrc="squareish.mp4"media="(min-aspect-ratio: 0.95) and (max-aspect-ratio: 1.05)"/><sourcesrc="portrait.mp4"media="(orientation: portrait)"/><sourcesrc="landscape.mp4"/></video>
This code creates a video with three sources: squareish.mp4 which is shown to people on “squareish” viewports, failing that portrait.mp4 which is shown to
people whose viewports are taller than wide, and failing that landscape.mp4 which is shown to anybody else.
That’s broadly-speaking how the video above is rendered. No JavaScript needed.
Browsers only handle media queries on videos when they initially load, so you can’t just tip your phone over or resize the window: you’ll need to reload the page, too. But it works!
Give it a go: take a look at the video in both portrait and landscape modes and let me know what you think1.
Adding adaptive bitrate streaming with HLS
Here’s another cool technology that you might not have realised you could “just use”: adaptive bitrate streaming with HLS!
You’ve used adaptive bitrate streaming before, though you might not have noticed it. It’s what YouTube, Netflix, etc. are doing when your network connection degrades and you quickly get
dropped-down, mid-video, to a lower-resolution version2.
Turns out you can do it on your own static hosting, no problem at all. I used this guide (which has a great
description of the parameters used) to help me:
This command splits the H.264 video landscape.mp4 into three different resolutions: the original “v1” (1920×1080, in my case, with 96kbit audio), “v2” (1280×720, with
96kbit audio), and “v3” (640×360, with 48kbit audio), each with a resolution-appropriate maximum bitrate, and forced keyframes every 48th frame. Then it breaks each of those into HLS
segments (.ts files) and references them from a .m3u8 playlist.
The output from this includes:
Master playlist landscape.m3u8, which references the other playlists with reference to their resolution and bandwidth, so that browsers can make smart choices,
Playlists landscape_0.m3u8 (“v1”), landscape_1.m3u8 (“v2”), etc., each of which references the “parts” of that video,
Directories landscape_0/, landscape_1/ etc., each of which contain
data00.ts, data01.ts, etc.: the actual “chunks” that contain the video segments, which can be downloaded independently by the browser as-needed
Bringing it all together
We can bring all of that together, then, to produce a variable-aspect, adaptive bitrate, HLS-streamed video player… in pure HTML and suitable for static hosting:
<videocontrols><sourcesrc="squareish.m3u8"type="application/x-mpegURL"media="(min-aspect-ratio: 0.95) and (max-aspect-ratio: 1.05)"/><sourcesrc="portrait.m3u8"type="application/x-mpegURL"media="(orientation: portrait)"/><sourcesrc="landscape.m3u8"type="application/x-mpegURL"/></video>
You could, I suppose, add alternate types, poster images, and all kinds of other fancy stuff, but this’ll do for now.
One solution is to also provide the standard .mp4 files as an alternate <source>, and that’s fine I guess, but you lose the benefit of HLS (and
you have to store yet more files). But there’s a workaround:
Polyfill full functionality for all browsers
If you’re willing to use a JavaScript polyfill, you can make the code above work on virtually any device. I gave this a go, here, by:
Adding some JavaScript code that detects affected `<video>` elements and applying the fix if necessary:
// Find all <video>s which have HLS sources:for( hlsVideo of document.querySelectorAll('video:has(source[type="application/x-mpegurl"]), video:has(source[type="vnd.apple.mpegurl"])') ) {
// If the browser has native support, do nothing:if( hlsVideo.canPlayType('application/x-mpegurl') || hlsVideo.canPlayType('application/vnd.apple.mpegurl') ) continue;
// If hls.js can't help fix that, do nothing:if ( ! Hls.isSupported() ) continue;
// Find the best source based on which is the first one to match any applicable CSS media queriesconst bestSource =Array.from(hlsVideo.querySelectorAll('source')).find(source=>window.matchMedia(source.media).matches)
// Use hls.js to attach the best source:const hls =new Hls();
hls.loadSource(bestSource.src);
hls.attachMedia(hlsVideo);
}
It makes me feel a little dirty to make a <video>depend on JavaScript, but if that’s the route you want to go down while we wait for HLS support to become
more widespread (rather than adding different-typed sources) then that’s fine, I guess.
This was a fun dive into some technologies I’ve not had the chance to try before. A fringe benefit of being a generalist full-stack developer is that when you’re “between jobs”
you get to play with all the cool things when you’re brushing up your skills before your next big challenge!
(Incidentally: if you think you might be looking to employ somebody like me, my CV is over there!)
Footnotes
1 There definitely isn’t a super-secret “square” video on this page, though. No
siree. (Shh.)
2 You can tell when you get dropped to a lower-resolution version of a video because
suddenly everybody looks like they’re a refugee from Legoland.
I’m keeping an eye out for my next career move (want to hire me?). Off the back of that I’ve been brushing up on the kinds of skills that I might be asked to showcase
in any kind of “tech test”.
Not the kind of stuff I can do with one hand tied behind my back1,
but the things for which I’d enjoy feeling a little more-confident2.
Stuff that’s on my CV that I’ve done and can do, but where I’d like to check before somebody asks me about it in an interview.
React? Sure, I can do that…
LinkedIn, GlassDoor, and bits of the Fediverse are a gold mine for the kinds of things that people are being asked to demonstrate in tech tests these days. Like this post:
I’d describe myself as a “stack-agnostic senior/principal full-stack/backend web developer/security engineer”3,
and so this question – which feels like it’s a filter for a junior developer with a React specialisation – isn’t really my wheelhouse. Which makes it a perfect excuse for an hour of
playing about with React.
My recent React experience has mostly involved Gutenberg blocks and WordPress theme component. This seemed like an excuse to check that I can wrangle a non-WordPress React stack.
This isn’t particularly sophisticated. I added customisable durations for each light, but otherwise it’s pretty basic.
Half an hour later, I’d proven to myself that yes, I could throw together a fresh application with React DOM and implement some React components, pass state around and whatnot.
Time to move on to the next thing, right? That’s what a normal person would do.
But that’s not the kind of person I am.
Let’s reimplement this as Web Components
What I found myself thinking was… man, this is chunky. React is… not the right tool for this job.
(Or, increasingly, any job. But I’ll get back to that.)
A minified production build of my new component and its dependencies came in at 202kB (62.3kB compressed). That feels pretty massive for something that does so-little.
So as an experiment, I re-implemented my new React component as a vanilla JS Web Component using a custom element. Identical functionality, but no third-party library dependencies.
Here’s what I got:
This one’s interactive. Press a button or two!
The Web Component version of this control has no dependency chain and uses no JSX, and so it has no transpilation step: the source version is production-ready. You could minify it, but
modern HTTP compression makes the impact of that negligible anyway: the whole thing weighs in at 19.5kB (5.2kB compressed) without minification.
And while I appreciate of course that there’s much more to JavaScript complexity and performance than file sizes… and beyond that I appreciate that there’s a lot more to making great
components than the resulting bundle size… it’s hard to argue that delivering the same functionality (and less fragility) in a twelfth of the payload isn’t significant.
By any metric you like, the Web Components version outperforms the React version of my traffic light component. And while it’s a vastly-simplified example, it scales. Performance is a
UX concern, and if you favour “what we’re familiar with” over “what’s best for our users”, that has to be a conscious choice.
But there’s a bigger point here:
React is the new jQuery
I’m alarmed by the fact that I’m still seeing job ads for “React developers”, with little more requirement than an ability to “implement things in React”.
From where I’m sitting, React is the new jQuery. It:
Was originally built to work around missing or underdeveloped JavaScript functionality
e.g. React’s components prior to Web Components
e.g. jQuery’s manipulation prior to document.querySelectorAll
Continued to be valuable as a polyfill and as a standard middleware while that functionality become commonplace
e.g. jQuery’s $.ajax until the Fetch API was a reliable replacement to XMLHttpRequest
No longer provides enough value to be worth using in a new project
And yet somehow gets added “out of habit” for many years
If you’ve got a legacy codebase with lots of React in it, you’re still going to need React for a while. Just like how you’re likely to continue to need jQuery for a while until you can
tidy up all those edge-cases where you’re using it.
(You might even be locked-in to using both React and jQuery for some time, if say you’ve got a plugin architecture that demands backwards-compatibility: I’m looking at you,
WordPress!)
But just as you’re already (hopefully) working to slowly extricate your codebases from any now-unnecessary jQuery dependencies they have… you should be working on an exit plan for your
React code, too. It’s done its time; it’s served its purpose: now it’s just a redundant dependency making your bundles cumbersome and harder to debug.
Everything React gives you on the client-side – components, state/hooks, routing4,
etc. – is possible (and easy) in modern JavaScript supported in all major browsers. And if you still really want an abstraction layer, there are plenty of options (and they’re
all a lot lighter than React!).
The bottom line is, I suppose…
You shouldn’t be hiring “React developers”!
If you’re building a brand new project, you shouldn’t be using React. It should be considered deprecated.
If you’ve got an existing product that depends on React… you should be thinking about how you’ll phase it out over time. And with that in mind, you want to be hiring versatile
developers. They’ll benefit from some experience with React, sure, but unless they can also implement for the modern Web of tomorrow, they’ll just code you deeper into
your dependency on React.
It’s time you started recruiting “Front-End Developers (React experience a plus)”. Show some long-term thinking! Or else the Web is going to move on without you, and in 5-10 years
you’ll struggle to recruit people to maintain your crumbling stack.
1 Exploiting or patching an injection vulnerability, optimising an SQL query, implementing
a WordPress plugin, constructing a CircleCI buildchain, expanding test coverage over a Rubygem, performing an accessibility audit of a web application, extending a set of
high-performance PHP-backed REST endpoints, etc. are all – I’d hope! – firmly in the “hold my beer” category of tech test skills I’d ace, for example. But no two tech stacks are
exactly alike, so it’s possible that I’ll want to brush up on some of the adjacent technologies that are in the “I can do it, but I might need to hit the docs pages”
category.
2 It’s actually refreshing to be learning and revising! I’ve long held that I should learn
a new programming language or framework every year or two to stay fresh and to keep abreast of what’s going on in world. I can’t keep up with every single new front-end JavaScript
framework any more (and I’m not sure I’d want to!)! But in the same way as being multilingual helps unlock pathways to more-creative thought and expression even if you’re only working
in your native tongue, learning new programming languages gives you a more-objective appreciation of the strengths and weaknesses of what you use day-to-day. tl;dr: if you haven’t
written anything in a “new” (to you) programming language for over a year, you probably should.
3 What do job titles even mean, any more? 😂 A problem I increasingly find is that I don’t
know how to describe what I do, because with 25+ years of building stuff for the Web, I can use (and have used!) most of the popular stacks, and could probably learn a new
one without too much difficulty. Did I mention I’m thinking about my next role? If you think we might “click”, I’d love to hear from you…
4 Though if you’re doing routing only on the client-side, I already hate you.
Consider for example the SlimJS documentation which becomes completely unusable if a third-party JavaScript CDN fails: that’s pretty
fragile!
Today, Ruth and JTA received a letter. It told them about an upcoming change to the
agreement of their (shared, presumably) Halifax credit card.
Except… they don’t have a shared Halifax credit card. Could it be a scam? Some sort of phishing attempt, maybe, or perhaps somebody taking out a credit card in their names?
I happened to be in earshot and asked to take a look at the letter, and was surprised to discover that all of the other details – the last four digits of the card, the credit
limit, etc. – all matched my Halifax credit card.
Halifax sent a letter to me, about my credit card… but addressed it to… two other people I live with‽
I spent a little over half an hour on the phone with Halifax, speaking to two different advisors, who couldn’t fathom what had happened or how. My credit card is not (and has never
been) a joint credit card, and the only financial connection I have to Ruth and JTA is that I share a mortgage with them. My guess is that some person or computer at Halifax tried to
join-the-dots from the mortgage outwards and re-assigned my credit card to them, instead?
Eventually I had to leave to run an errand, so I gave up on the phone call and raised a complaint with Halifax in writing. They’ve promised to respond within… eight weeks. Just
brilliant.
I’ve had a few breakups, but I’ve only been made redundant once. There’s a surprising overlap between the two…
And with that, I’d better get back to it. Today’s mission is to finish checking-in on my list of “companies I’ve always admired and thought I should work for” and see if any of them are
actively looking for somebody like me!
(Incidentally: if you’re into open source, empowering the Web, and making the world a better place, my CV is over here. I’m a senior/principal full-stack
engineer with a tonne of experience in some radically diverse fields, and if you think we’d be a good match then I’d love to chat!)
Sure, it’s gaudy, but it’s got a few things going for it, too.
Let’s put aside for the moment that you can already send my website back into “90s mode” and dive into this take on how I could
present myself in a particularly old-school way. There’s a few things I particularly love:
It’s actually quite lightweight: ignore all the animated GIFs (which are small anyway) and you’ll see that, compared to my current homepage, there are very few
images. I’ve been thinking about going in a direction of less images on the homepage anyway, so it’s interesting to see how it comes together in this unusual context.
The page sections are solidly distinct: they’re a mishmash of different widths, some of which exhibit a horrendous lack of responsivity, but it’s pretty clear where
the “recent articles” ends and the “other recent stuff” begins.
The post kinds are very visible: putting the “kind” of a post in its own column makes it really clear whether you’re looking at an article, note, checkin, etc., much
more-so than my current blocks do.
Maybe there’s something we can learn from old-style web design? No, I’m serious. Stop laughing.
90s web design was very-much characterised by:
performance – nobody’s going to wait for your digital photos to download on narrowband connections, so you hide them behind descriptive links or tiny thumbnails, and
pushing the boundaries – the pre-CSS era of the Web had limited tools, but creators worked hard to experiment with the creativity that was possible within those
limits.
Those actually… aren’t bad values to have today. Sure, we’ve probably learned that animated backgrounds, tables for layout, and mystery meat navigation were horrible for
usability and accessibility, but that doesn’t mean that there isn’t still innovation to be done. What comes next for the usable Web, I wonder?
As soon as you run a second or third website through the tool, its mechanisms for action become somewhat clear and sites start to look “samey”, which is the opposite of what
made 90s Geocities great.
The only thing I can fault it on is that it assumes that I’d favour Netscape Navigator: in fact, I was a die-hard Opera-head for most of the
nineties and much of the early naughties, finally switching my daily driver to Firefox in 2005.
I certainly used plenty of Netscape and IE at various points, though, but I wasn’t a fan of the divisions resulting from the browser wars. Back in the day, I always backed
the ideals of the “Viewable With Any Browser” movement.
You’ve probably come across GeoGuessr already: it’s an online game where you (and friends, if you’ve got them) get dropped into Google Street
View and have two minutes to try to work out where in the world you are and drop a pin on it.
Can you tell where we are, yet?
A great strategy is to “walk around” a little, looking for landmarks, phone numbers, advertisements, linguistic clues, cultural indicators, and so on, narrowing down the region of the
world you think you’re looking at before committing to a country or even a city. You’re eventually scored by how close you are to the actual location.
Cheating at GeoGuessr
I decided to see if ChatGPT can do better than me. Using only the free tier of both GeoGuessr and ChatGPT1, I pasted
screenshots of what I was seeing right into ChatGPT:
ChatGPT confidently assessed the geographic clues, translated some text that it found, and eventually made a guess down to a particular street in St Petersburg.
That’s pretty spooky, right?
The response came back plenty fast enough for me to copy-and-paste the suggested address into Google Maps, get the approximate location, and then drop a pin in the right place in
GeoGuessr. It’s probably one of my most-accurate guesses ever.
This isn’t a one-off fluke. I tried again, this time using only a single photo, rather than one pointing in each direction on the street:
Again, the text recognition and translation capabilities of the AI were highly useful, but it was helped by architectural and cultural clues too.
This time, it wasn’t quite right: the actual location of the photo was Chittagong, not Dhaka, about 200km away.
But that’s still reasonably spectacular from only a single vantage from a single point.
Don’t think I’d have done better, though.
Obviously my approach here was crude, but it’d be relatively easy to, for example, implement a browser wrapper that cheated on-your-behalf: while playing GeoGuessr, you’d just click a
“send to AI” button whenever you fancied and it’d start working in the background, improving precision with each subsequent screenshot (so you could still “walk around” and pass extra
details to it).
And similarly, a little prompt manipulation could have the output include estimated GPS coordinates, allowing the code to place the pin for you while outputting its reasoning
on the side2.
The short of what I’m saying is: if you’re playing GeoGuessr against somebody you don’t trust not to cheat… they might well be cheating. And thanks to the explanatory output, they can
even justify their explanations for the places they dropped pins.
What about other photos?
The other thought that comes to my mind is: could this be used to infer approximate geolocations from photos whose EXIF metadata has been stripped. Because if so, that’s the
kind of thing that’s certain to get exploited by all kind of people who want to know where you are/were at a particular time. For example… law enforcement, stalkers, and
other unsavoury types.
Explanation: The photograph shows a large ship docked at a port with a building that displays the text “WELCOME TO PORT OF SPAIN”. This text is in English,
indicating an English-speaking country. The mention of “Port of Spain” directly specifies the port’s location in the capital city of Trinidad and Tobago. The design and style of
the port facilities, as well as the presence of a ship named “Logos Hope”, which is known to visit many ports globally, further suggests a Caribbean port, aligning with Port of
Spain’s known characteristics.
Location: The Rollright Stones, England, United Kingdom
Explanation: The photograph depicts an area with several ancient standing stones arranged in a circle in a rural setting, characteristic of a stone circle.
These are typically found in certain parts of the UK. The terrain is typical of the British countryside, with a grassy field and surrounding trees. The specific arrangement
and size of the stones, along with the style of fencing and walking paths, are reminiscent of the Rollright Stones, one of Britain’s historic sites known for a circle of
Neolithic or Bronze Age standing stones located in Oxfordshire, England.
Coordinates: 51.9743, -1.5731
✅ Again, spot on. If you’d never been to the Rollright Stones, you probably wouldn’t get that one, because while it’s a distinctive-looking stone circle… it’s not that
distinctive-looking, right? Let’s be honest: it’s some rocks in a field.
Explanation: The photograph prominently features the Galata Tower in the background, a well-known landmark in Istanbul, Turkey. Moreover, the presence of a ferry
or similar boat and the architectural style of the surrounding buildings are indicative of Istanbul’s famous skyline. The signage in Turkish, as suggested by the word partially
visible on the left, also supports this location as Turkey is a predominantly Turkish-speaking country. These elements combined make it highly likely that the photograph was taken
in Istanbul.
Coordinates: 41.0082, 28.9784
✅ The coordinates aren’t exactly right – it’s placed us in the city rather than on a boat, which we clearly are – but it’s not done badly. Spotting the Galata Tower3 was a nice move.
Location: Cardiff Bay, Cardiff, Wales, United Kingdom
Explanation: The photograph features a marina with modern residential buildings, which is characteristic of the Cardiff Bay area in Cardiff, Wales. The
architecture, clear blue skies, and marina setting are reminiscent of Cardiff’s waterfront development. Additionally, the presence of English signage on the boat (“FINBAR”)
supports a location in an English-speaking country. Cardiff Bay is known for its redeveloped waterfront area with modern apartments and leisure facilities surrounding the marina.
The style and design of the building are consistent with developments in Cardiff’s revitalized docklands.
Coordinates: 51.4626, -3.1678
❌ Oops! Nope. I can see the thinking of what it’s claiming, there, but this was actually the Ipswich marina. I went for a walk to take a break from the code I’d been writing
and took this somewhere in the vicinity of the blue plaque for Edward Ardizzone that I’d just spotted (I was
recording a video for my kids, who’ve enjoyed several of his Tim… books).
So I don’t think this is necessarily a game-changer for Internet creeps yet. So long as you’re careful not to post photos in which you’re in front of any national monuments and
strip your EXIF metadata as normal, you’re probably not going to give away where you are quite yet.
Footnotes
1 And in a single-player game only: I didn’t actually want to cheat anybody out
of a legitimate victory!
2 I’m not going to implement GeoCheatr, as I’d probably name it. Unless somebody
feels like paying me to do so: I’m open for freelance work right now, so if you want to try to guarantee the win at the GeoGuessr World Championships (which will involve the much-riskier act of cheating in
person, so you’ll want a secret UI – I’m thinking a keyboard shortcut to send data to the AI, and an in-ear headphone so it can “talk” back to you?), look me up? (I’m mostly
kidding, of course: just because something’s technically-possible doesn’t mean it’s something I want to do, even for your money!)
4 3Camp is Three Rings‘ annual volunteer
get-together, hackathon, and meetup. People come together for an intensive week of making-things-better for charities the world over.
My star sign is Aquarius. Aquarians are, according to tradition: deep, imaginative, original, and uncompromising. That sounds like a pretty good description of me, right?
You can tell that I’m an Aquarius, because I’ve got a certificate to say so.
Now some of you might be thinking, “Hang on, wasn’t Dan born very close to the start of the year, and wouldn’t that make him a Capricorn, not an Aquarius?” I can understand why you’d
think that.
And while it’s true that I was assigned the star sign of Capricorn at my birth, it doesn’t really represent me very well. Capricorns are, we’re told, serious, disciplined, and good with
money. Do any of those things remotely sound like me? Not so much.
So many, many years ago I changed my star sign to Aquarius (I can’t remember exactly when, but I’d done it a long while
before I wrote the linked blog post, which in turn is over 14 years old…).
It doesn’t say anything in here to suggest that I can’t change my star sign.
But really: who has the right to tell you what your place in the zodiac is, really? Just you.
And frankly, people telling you who you can and can’t be is so last millennium. By now, there’s really no excuse for not accepting somebody’s identity, whether it’s for
something as trivial as their star sign… or as important as their gender, sexuality, or pronouns.
In hindsight, I probably should have launched this website yesterday and called it an April Fool. But I completely forgot that I’d planned to until an entire day afterwards,
so you get it now.
All of which is to say: I’ve launched a(nother) stupid website, ChangeYourStarSign.com. Give it a go!
It’s lightweight, requires no JS or cookies, does no tracking, and can run completely offline or be installed to your device, and it makes it easier than ever for you to change your
star sign. Let’s be honest: it was pretty easy anyway – just decide what your new star sign is – but if you’d rather have a certificate to prove it, this site’s got you
covered.
Whether you change your star sign to represent you better, to sidestep an unfortuitous horoscope (or borrow a luckier one), or for some other reason, I’d love to hear what you change it
to and how you get on with it. What’s your new star sign?
Here in the UK, ice cream vans will usually play a tune to let you know they’re set up and selling1.
So when you hear Greensleeves (or, occasionally, Waltzing Matilda), you know it’s time to go and order yourself a ninety-nine.
Imagine my delight, then, when I discover this week that ice cream vans aren’t the only services to play such jaunty tunes! I was sat with work colleagues outside İlter’s Bistro on Meşrutiyet Cd. in Istanbul, enjoying a beer, when a van
carrying water pulled up and… played a little song!
And then, a few minutes later – as if part of the show for a tourist like me – a flatbed truck filled with portable propane tanks pulled up. Y’know, the kind you might use to heat a
static caravan. Or perhaps a gas barbeque if you only wanted to have to buy a refill once every five years. And you know what: it played a happy little jingle, too. Such joy!
In Istanbul, people put out their empty water bottles to be swapped-out for full ones by the water delivery man2.
My buddy Cem, who’s reasonably local to the area, told me that this was pretty common practice. The propane man, the water man, etc. would
all play a song when they arrived in your neighbourhood so that you’d be reminded that, if you hadn’t already put your empties outside for replacement, now was the time!
And then Raja, another member of my team, observed that in his native India, vegetable delivery trucks also play a song so you know they’re arriving. Apparently the tune they
play is as well-standardised as British ice cream vans are. All of the deliveries he’s aware of across his state of Chennai play the same piece of music, so that you know it’s them.
Raja didn’t have a photo to share (and why would he? it’s not like I have a photo of the guy who comes to refill the gas tank behind my
house!3), so I found this stock pic which sounds a bit like what
he described. Photo courtesy Aiden Jones, used under a CC-By-SA license.
It got me thinking: what other delivery services might benefit from a recognisable tune?
Bin men: I’ve failed to put the bins out in time frequently enough, over the course of my life, that a little jingle to remind me to do so would be welcome4!
(My bin men often don’t come until after I’m awake anyway, so as long as they don’t turn the music on until after say 7am they’re unlikely to be a huge inconvenience to anybody,
right?) If nothing else, it’d cue me in to the fact that they were passing so I’d remember to bring the bins back in again afterwards.
Fish & chip van: I’ve never made use of the mobile fish & chip van that tours my village once a week, but I might be more likely to if it announced its arrival with a
recognisable tune.
I’m thinking a chorus of Baby Shark would get everybody’s attention.
Milkman: I’ve a bit of a gripe with our milkman. Despite promising to deliver before 07:00 each morning, they routinely turn up much later. It’s particularly
troublesome when they come at about 08:40 while I’m on the school run, which breaks my routine sufficiently that it often results in the milk sitting unseen on the porch until I think
to check much later in the day. Like the bin men, it’d be a convenience if, on running late, they at least made their presence in my village more-obvious with a happy little ditty!
Emergency services: Sirens are boring. How about if blue light services each had their own song. Perhaps something thematic? Instead of going nee-naw-nee-naw, you’d
hear, say, de-do-do-do-de-dah-dah-dah
and instantly know that you were hearing The Police.
Evri: Perhaps there’s an appropriate piece of music that says “the courier didn’t bother to ring your doorbell, so now your parcel’s hidden in your recycling box”?
Just a thought.
Anyway: the bottom line is that I think there’s an untapped market for jolly little jingles for all kinds of delivery services, and Turkey and India are clearly both way ahead
of the UK. Let’s fix that!
Footnotes
1 It’s not unheard of for cruel clever parents to try to teach their young
children that the ice cream van plays music only to let you know it’s soldout of ice cream. A devious plan, although one I wasn’t smart (or evil?) enough to try for
myself.
3 My gas delivery man should also have his own song, of course. Perhaps an instrumental
cover of Burn Baby Burn?
4 Perhaps bin men could play Garbage Truck by Sex Bob-Omb/Beck? That seems kinda
fitting. Although definitely not what you want to be woken up with if they turn the speakers on too early…
The news has, in general, been pretty terrible lately.
Like many folks, I’ve worked to narrow the focus of the things that I’m willing to care deeply about, because caring about many things is just too difficult when, y’know, nazis
are trying to destroy them all.
I’ve got friends who’ve stopped consuming news media entirely. I’ve not felt the need to go so far, and I think the reason is that I already have a moderately-disciplined
relationship with news. It’s relatively easy for me to regulate how much I’m exposed to all the crap news in the world and stay focussed and forward-looking.
The secret is that I get virtually all of my news… through my feed reader (some of it pre-filtered, e.g. my de-crappified BBC News feeds).
I use FreshRSS and I love it. But really: any feed reader can improve your relationship with
the Web.
Without a feed reader, I can see how I might feel the need to “check the news” several times a day. Pick up my phone to check the time… glance at the news while I’m there… you know how
to play that game, right?
But with a feed reader, I can treat my different groups of feeds like… periodicals. The news media I subscribe to get collated in my feed reader and I can read them once, maybe twice
per day, just like a daily newspaper. If an article remains unread for several days then, unless I say otherwise, it’s configured to be quietly archived.
My current events are less like a firehose (or sewage pipe), and more like a bottle of (filtered) water.
Categorising my feeds means that I can see what my friends are doing almost-immediately, but I don’t have to be disturbed by anything else unless I want to be. Try getting that
from a siloed social network!
Maybe sometimes I see a new breaking news story… perhaps 12 hours after you do. Is that such a big deal? In exchange, I get to apply filters of any kind I like to the news I read, and I
get to read it as a “bundle”, missing (or not missing) as much or as little as I like.
On a scale from “healthy media consumption” to “endless doomscrolling”, proper use of a feed reader is way towards the healthy end.
If you stopped using feeds when Google tried to kill them, maybe it’s time to think again. The ecosystem’s alive and well, and having a one-stop place where you can
enjoy the parts of the Web that are most-important to you, personally, in an ad-free, tracker-free, algorithmic-filtering-free space that you can make your very own… brings a
special kind of peace that I can highly recommend.
The W3C‘s WebDX Community Group this week announced that they’ve reached a milestone with their web-features project. The project is an effort to catalogue browser support for Web features, to establish an
understanding of the baseline feature set that developers can rely on.
That’s great, and I’m in favour of the initiative. But I wonder about graphs like this one:
The graph shows the increase in time of the number of features available on the Web, broken down by how widespread they are implemented across the browser corpus.
The shape of that graph sort-of implies that… more features is better. And I’m not entirely convinced that’s true.
Does “more” imply “better”?
Don’t get me wrong, there are lots of Web features that are excellent. The kinds of things where it’s hard to remember how I did without them. CSS grids are for many purposes an
improvement on flexboxes; flexboxes were massively better than floats; and floats were an enormous leap forwards compared to using tables for layout! The “new” HTML5 input types are
wonderful, as are the revolutionary native elements for video, audio, etc. I’ll even sing the praises of some of the new JavaScript APIs (geolocation, web share, and push are
particular highlights).
But it’s not some kind of universal truth that “more features means better developer experience”. It’s already the case, for example, that getting started as a Web developer is
harder than it once was, and I’d argue harder than it ought to be. There exist complexities nowadays that are barriers to entry. Like the places where the promise of a
progressively-enhanced Web has failed (they’re rare, but they exist). Or the sheer plethora of features that come with caveats to their use that simply must be learned (yes, you need a
<meta name="viewport">; no, you can’t rely on JS to produce content).
Meanwhile, there are technologies that were standardised, and that we did need, but that never took off. The <keygen> element never got
implemented into the then-dominant Internet Explorer (there were other implementation problems too, but this one’s the killer). This made it functionally useless, which meant that its
standard never evolved and grew. As a result, its implementation in other browsers stagnated and it was eventually deprecated. Had it been implemented properly and iterated on, we’d
could’ve had something like WebAuthn over a decade earlier.
Which I guess goes to show that “more features is better” is only true if they’re the right features. Perhaps there’s some way of tracking the changing landscape of developer
experience on the Web that doesn’t simply count enumerate a baseline of widely-available features? I don’t know what it is, though!
A simple web
Mostly, the Web worked fine when it was simpler. And while some of the enhancements we’ve seen over the decades are indisputably an advancement, there are also plenty of places
where we’ve let new technologies lead us astray. Third-party cookies appeared as a naive consequence of first-party ones, but came to be used to undermine everybody’s privacy. Dynamic
DOM manipulation started out as a clever idea to help with things like form validation and now a significant number of websites can’t even show their images – or sometimes their text –
unless their JavaScript code gets downloaded and interpreted successfully.
Were you reading this article on Medium, you’d have downloaded ~5MB of data including 48 JS files and had 7 cookies set, just so you could… have most of the text covered with
popovers? (for comparison, reading it here takes about half a megabyte and the cookies are optional delicious)
A blog post, news article, or even an eCommerce site or social networking platform doesn’t need the vast majority of the Web’s “new” features. Those features are important for some Web
applications, but most of the time, we don’t need them. But somehow they end up being used anyway.
Whether or not the use of unnecessary new Web features is a net positive to developer experience is debatable. But it’s certainly not often to the benefit of user experience.
And that’s what I care about.
Last month my pest of a dog destroyed my slippers, and it was more-disruptive to my life than I would have anticipated.
Look what you did, you troublemaker.
Sure, they were just a pair of slippers1, but they’d
become part of my routine, and their absence had an impact.
Routines are important, and that’s especially true when you work from home. After I first moved to Oxford and started doing entirely remote work for the first time, I found the transition challenging2.
To feel more “normal”, I introduced an artificial “commute” into my day: going out of my front door and walking around the block in the morning, and then doing the same thing in reverse
in the evening.
My original remote working office, circa 2010.
It turns out that in the 2020s my slippers had come to serve a similar purpose – “bookending” my day – as my artificial commute had over a decade earlier. I’d slip them on when I was at
my desk and working, and slide them off when my workday was done. With my “work” desk being literally the same space as my “not work” desk, the slippers were a psychological reminder of
which “mode” I was in. People talk about putting on “hats” as a metaphor for different roles and personas they hold, but for me… the distinction was literal footwear.
And so after a furry little monster (who for various reasons hadn’t had her customary walk yet that day and was probably feeling a little frustrated) destroyed my slippers… it actually
tripped me up3. I’d be doing
something work-related and my feet would go wandering, of their own accord, to try to find their comfortable slip-ons, and when they failed, my brain would be briefly tricked
into glancing down to look for them, momentarily breaking my flow. Or I’d be distracted by something non-work-related and fail to get back into the zone without the warm, toe-hugging
reminder of what I should be doing.
It wasn’t a huge impact. But it wasn’t nothing either.
The bleppy little beast hasn’t expressed an interest in my replacement slippers, yet. Probably because they’re still acquiring the smell of my feet, which I’m guessing is
what interested her in the first place.
So I got myself a new pair of slippers. They’re a different design, and I’m not so keen on the lack of an enclosed heel, but they solved the productivity and focus problem I was facing.
It’s strange how such a little thing can have such a big impact.
Oh! And d’ya know what? This is my hundredth blog post of the year so far! Coming on only the 73rd day of the year, this is my fastest run at
#100DaysToOffload yet (my previous best was last year, when I managed the same on 22 April). 73 is exactly a fifth of 365, so… I guess I’m on
track for a mammoth 500 posts this year? Which would be my second-busiest blogging year ever, after 2018. Let’s see how I get on…4
Footnotes
1 They were actually quite a nice pair of slippers. JTA got them for me as a gift a few years back, and they lived either on my feet or under my desk ever since.
2 I was working remotely for a company where everybody else was working
in-person. That kind of hybrid setup is a lot harder to do “right”, as many companies in this post-Covid-lockdowns age have discovered, and it’s understandable that I found it
somewhat isolating. I’m glad to say that the experience of working for my current employer – who are entirely distributed –
is much more-supportive.
3 Figuratively, not literally. Although I would probably have literally tripped
over had I tried to wear the tattered remains of my shredded slippers!
As soon as I finished reading its prequel, I started reading Becky Chambers’ A Prayer for the Crown-Shy (and then, for
various work/life reasons, only got around to publishing my micro-review just now).
The book carries on directly from where A Psalm for the Wild-Built left off, to such a degree that at first I wondered whether the pair might have been better published as a
single volume. But in hindsight, I appreciate the separation: there’s a thematic shift between the two that benefits from a little (literal) bookending.
Both Wild-Built and Crown-Shy look at the idea of individual purpose and identity, primarily through the vehicle of relatable protagonist Sibling Dex as they
very-openly seek their place in the world, and to a lesser extent through the curiosity and inquisitiveness of the robot Mosscap.
But the biggest difference in my mind between the ways in which the two do so is the source of the locus of evaluation: the vast majority of Wild-Built is experienced only by
Dex and Mosscap, alone together in the wilderness at the frontier between their disparate worlds. It maintains an internal locus of evaluation, with Dex asking questions of themselves
about why they feel unfulfilled and Mosscap acting as a questioning foil and supportive friend. Crown-Shy, by contrast, pivots to a perceived external locus of evaluation:
Dex and Mosscap return from the wilderness to civilisation, and both need to adapt to the experience of celebrity, questioning, and – in Mosscap’s case – a world completely-unfamiliar
to it.
By looking more-carefully at Dex’s society, the book helps to remind us about the diverse nature of humankind. For example: we’re shown that even in a utopia, individual people will
disagree on issues and have different philosophical outlooks… but the underlying message is that we can still be respectful and kind to one another, despite our disagreement.
In the fourth chapter, the duo visit a coastland settlement whose residents choose to live a life, for the most part, without the convenience of electricity. By way of deference to
their traditions, Dex (with their electric bike) and Mosscap (being an electronic entity) wait outside the village until invited in by one of the residents, and the trio enjoy a
considerate discussion about the different value systems of people around the continent while casting fishing lines off a jetty. There’s no blame; no coercion; and while it’s implied
that other residents of the village are staying well clear of the visitors, nothing more than this exclusion and being-separate is apparent. There’s sort-of a mutual assumption that
people will agree-to-disagree and get along within the scope of their shared vision.
Which leads to the nub of the matter: while it appears that we’re seeing how Dex is viewed by others – by those they disagree with, by those who hold them with some kind of
celebrity status, by their family with whom they – like many folks do – share a loving but not uncomplicated relationship – we’re actually still experiencing
this internally. The questions on Dex’s mind remain “who am I?”, “what is my purpose?”, and “what do I want?”… questions only they can answer… but now they’re
considering them from the context of their relationship with everybody else in their world, instead of their relationship with themself.
Everything I just wrote reads as very-pretentious, for which I apologise. The book’s much better-written than my review! Let me share a favourite passage, from a part of the book where
Dex is introducing Mosscap to ‘pebs’, a sort-of currency used by their people, by way of explanation as to why people whom Mosscap had helped had given it pieces of paper with numbers
written on (Mosscap not yet owning a computer capable of tracking its balance). I particularly love Mosscap’s excitement at the possibility that it might own things, an
experience it previous had no need for:
…
Mosscap smoothed the crease in the paper, as though it were touching something rare and precious. “I know I’m going to get a computer, but can I keep this as well?”
“Yeah,” Dex said with a smile. “Of course you can.”
“A map, a note, and a pocket computer,” Mosscap said reverently. “That’s three belongings.” It laughed. “I’ll need my own wagon, at this rate.”
“Okay, please don’t get that much stuff,” Dex said. “But we can get you a satchel or something, if you want, so you don’t have things rattling around inside you.”
Mosscap stopped laughing, and looked at Dex with the utmost seriousness. “Could I really?” it said quietly. “Could I have a satchel?”
…
That’s just a heartwarming and childlike response to being told that you’re allowed to own property of your very own. And that’s the kind of comforting joy that, like its prequel, the
entire book exudes.
A Prayer for the Crown-Shy is not quite so wondrous as A Psalm for the Wild-Built. How could it be, when we’re no longer quite so-surprised by the enthralling world in
which it’s set. But it’s still absolutely magnificent, and I can wholeheartedly recommend the pair.
Eleven years ago, comedy sketch The Expert had software engineers (and other misunderstood specialists) laughing to
tears at the relatability of Anderson’s (Orion Lee) situation: asked to do the literally-impossible by people who don’t understand
why their requests can’t be fulfilled.
Decades ago, a client wanted their Web application to automatically print to the user’s printer, without prompting. I explained that it was impossible because “if a website could print
to your printer without at least asking you first, everybody would be printing ads as you browsed the web”. The client’s response: “I don’t need you to let everybody
print. Just my users.”1
So yeah, I was among those that sympathised with Anderson.
In the sketch, the client requires him to “draw seven red lines, all of them strictly perpendicular; some with green ink and some with transparent”. He (reasonably) states that this is
impossible2.
Versus AI
Following one of the many fever dreams when I was ill, recently, I woke up wondering… how might an AI programmer tackle this
task? I had an inkling of the answer, so I had to try it:
Aside from specifying that I want to use JavaScript and a <canvas> element3, the
question is the same as in the sketch.
When I asked gpt-4o to assist me, it initially completely ignored the perpendicularity requirement.
Drawing all of the lines strictly parallel to one another was… well, the exact opposite of what was asked for, although it was at least possible.
Let’s see if it can do better, with a bit of a nudge:
This is basically how I’d anticipated the AI would respond: eager to please, willing to help, and with an eager willingness that completely ignored the infeasibility of the task.
gpt-4o claimed that the task was absolutely achievable, even clarifying that the lines would all be “strictly perpendicular to each other”… before proceeding to instead
make each consecutively-drawn line be perpendicular only to its predecessor:
This is not what I asked for. But more importantly, it’s not what I wanted. (But it is pretty much what I expected.)
You might argue that this test is unfair, and it is. But there’s a point that I’ll get to.
But first, let me show you how a different model responded. I tried the same question with the newly-released Claude 3.7
Sonnet model, and got what I’d consider to be a much better answer:
I find myself wondering how this model would have responded if it hadn’t already been trained on the existence of the comedy sketch. The answer that (a) it’s impossible but
(b) here’s a fun bit of code that attempts to solve it anyway is pretty-much perfect, but would it have come up with it on a truly novel (but impossible) puzzle?
In my mind: an ideal answer acknowledges the impossibility of the question, or at least addresses the supposed-impossibility of it. Claude 3.7 Sonnet did well here,
although I can’t confirm whether it did so because it had been trained on data that recognised the existence of “The Expert” or not (it’s clearly aware of the sketch, given its
answer).
Suppose I didn’t know that it was impossible to make seven lines perpendicular to one another in anything less than seven-dimensional space. If that were the case, it’d
be tempting to accept an AI-provided answer as correct, and ship it. And while that example is trivial (and at least a little bit silly), it’s the kind of thing that, I have no doubt,
actually happens in other areas.
Chatbots eagerness to provide a helpful answer, even if no answer is possible, is a huge liability. The other week, I experimentally asked Claude 3.5 for assistance with a
PHPUnit mocking challenge and it provided a whole series of answers… that were completely invalid! It later turned out that what I was trying to achieve was
impossible5.
Given that its answers clearly didn’t-work there was no risk I’d have shipped it anyway, but I’m certain that there exist developers who’ve asked a chatbot for help in a domain they
didn’t understood and accepted its answer while still not understanding it, which feels to me like a quick route to introducing into your code a bug that happy-path testing
won’t reveal. (Y’know, something like a security vulnerability, or an accessibility failure, or whatever.)
Code assisting AI remains really interesting and occasionally useful… but it’s also a real minefield and I see a lot of naiveté about its limitations.
Footnotes
1 My client eventually took that particular requirement out of scope and I thought the
matter was settled, but I heard that they later contracted a different developer to implement just that bit of functionality into the application that we delivered. I never
checked, but I think that what they delivered exploited ActiveX/Java applet vulnerabilities to achieve the goal.
2 Nerds gotta nerd, and so there’s been endless debate on the Internet about whether the
task is truly impossible. For example, when I first saw the video I was struck by the observation that perpendicularity within a set of lines is limited linearly by the
number of dimensions you’re working in, so it’s absolutely possible to model seven lines all perpendicular to one another… if you’re working in seven dimensions. But let’s put that
all aside for a moment and assume the task is truly impossible within some framework unspecified-but-implied within the universe of the sketch, ‘k?
3 Two-dimensionality feels like a fair assumed constraint, given that in the sketch
Anderson tries to demonstrate the challenges of the task by using a flip-chart.
4 I also don’t use AI to produce anything creative that I then pass off as my own,
because, y’know, many of these models don’t seem to respect copyright. You won’t find any AI-written content on my blog, for example, except specifically to demonstrate AI’s
capabilities (or lack thereof) when discussing AI, and this is always be clearly labelled. But that’s another question.
5 In fact, I was going about the problem itself in entirely the wrong way: some minor
refactoring later and I had some solid unit tests that fit the bill, and I didn’t need to do the impossible. But the AI never clocked that, and I suspect it never would have.
I’d already read every prior book published by the
excellent Becky Chambers, but this (and its sequel) had been sitting on my to-read list for some time, and so while I’ve been ill and off work these last few days, I felt it would be a perfect opportunity to pick it up. I’ve spent most of this week so far in bed, often drifting in and
out of sleep, and a lightweight novella that I coud dip in and out of over the course of a day felt like the ideal comfort.
I couldn’t have been more right, as the very first page gave away. My friend Ash described the experience of reading it (and
its sequel) as being “like sitting in a warm bath”, and I see where they’re coming from. True to form, Chambers does a magnificent job of spinning a believable utopia: a world that acts
like an idealised future while still being familiar enough for the reader to easily engage with it. The world of Wild-Built is inhabited by humans whose past saw them come
together to prevent catastrophic climate change and peacefully move beyond their creation of general-purpose AI, eventually building for themselves a post-scarcity economy based on
caring communities living in harmony with their ecosystem.
Writing a story in a utopia has sometimes been seen as challenging, because without anything to strive for, what is there for a protagonist to strive against? But
Wild-Built has no such problem. Written throughout with a close personal focus on Sibling Dex, a city monk who decides to uproot their life to travel around the various
agrarian lands of their world, a growing philosophical theme emerges: once ones needs have been met, how does one identify with ones purpose? Deprived of the struggle to climb
some Maslowian pyramid, how does a person freed of their immediate needs (unless they choose to take unnecessary risks: we hear of hikers who die exploring the uncultivated
wilderness Dex’s people leave to nature, for example) define their place in the world?
Aside from Dex, the other major character in the book is Mosscap, a robot whom they meet by a chance encounter on the very edge of human civilisation. Nobody has seen a robot for
centuries, since such machines became self-aware and, rather than consign them to slavery, the humans set them free (at which point they vanished to go do their own thing).
To take a diversion from the plot, can I just share for a moment a few lines from an early conversation between Dex and Mosscap, in which I think the level of mutual interpersonal
respect shown by the characters mirrors the utopia of the author’s construction:
…
“What—what are you? What is this? Why are you here?”
The robot, again, looked confused. “Do you not know? Do you no longer speak of us?”
“We—I mean, we tell stories about—is robots the right word? Do you call yourself robots or something else?”
“Robot is correct.”
…
“Okay. Mosscap. I’m Dex. Do you have a gender?”
“No.”
“Me neither.”
These two strangers take the time in their initial introduction to ensure they’re using the right terms for one another: starting with those relating to their… let’s say
species… and then working towards pronouns (Dex uses they/them, which seems to be widespread and commonplace but far from universal in their society; Mosscap uses it/its, which
provides for an entire discussion on the nature of objectship and objectification in self-identity). It’s queer as anything, and a delightful touch.
In any case: the outward presence of the plot revolves around a question that the robot has been charged to find an answer to: “What do humans need?” The narrative theme of self-defined
purpose and desires is both a presenting and a subtextual issue, and it carries through every chapter. The entire book is as much a thought experiment as it is a
novel, but it doesn’t diminish in the slightest from the delightful adventure that carries it.
Dex and Mosscap go on to explore the world, to learn more about it and about one another, and crucially about themselves and their place in it. It’s charming and wonderful and uplifting
and, I suppose, like a warm bath: comfortable and calming and centering. And it does an excellent job of setting the stage for the second book in the series, which we’ll get to presently…
So far, so good. But here’s the HTML code they’re using to create that button. Maybe you’ll spot
the problem:
RSS
Spotify
Pocket Casts
Apple Podcasts
YouTube
