Representation matters. That we have a trans former-judge, somebody both well-equipped and motivated to escalate this important challenge to the ECHR, is hugely
fortunate.
We need more representation (of trans people specifically, but many other groups too, and perhaps particularly in the intersections) in positions of power, expertise, and authority. To
defend the human rights of all of us.
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!)
Saw GCB61ZC “Mossy” appear yesterday, but I’d already had an Easter Sunday beer or two and couldn’t drive out here… in fact, I
realised, I probably wasn’t in a state to cycle out here either and so I resolved that I’d come out the following morning – that is, today – by car and give the dog a walk while finding
GL1E5FYX0 and its year-older sibling GCAR5HV “Ivy”.
But early this morning the dog had been poorly and was still needing to relieve herself with little to no notice, so I didn’t want to risk putting her in the car! Though… I did want to
keep her outdoors! It was time for a change in plan: instead of driving to near the cache then taking a walk… we’d attempt the whole thing on foot, perhaps taking the opportunity to
explore some of the back footpaths that we’d not yet had a chance to try. We’d now missed
our chance for the FTF at “Mossy”, but we could still enjoy a walk (and hopefully give the dog a chance to feel better).
We cut through fields at Sutton, past The Fox and Blackditch Farm, to brush against the side of Lakeside Industrial Estate and head down Dix Pit. After a brief pause to report fly
tipping at 51.745311, -1.412871 (why would anybody fly tip literally just down the road from the recycling centre? it boggles my mind), we decided to duck off the road and take the
parallel public footpath for a bit (OSM Way #204829432, trailhead 51.742330, -1.416563).
To our surprise, the public footpath was fenced off. I thought we might instead be able to take the track to the West and intersect with the nearby bridleway (OSM Way #1129092587) but it was marked as private, so we continued down Dix Pit. How DOES one get to that bridleway, I wondered? Just
out of curiosity we tried to join it via the footpath (OSM Way #1129092588) at 51.737047, -1.412766, but it, too, lacked a
usable gate (and looked severely overgrown!), although the public footpath signs within the mess were still visible. I suspect that this public footpath has been long neglected by the
landowner and is quickly becoming lost to the world.
Instead, then, we passed Cutmill Farm and took the footpath through the woods that straddle the boundary line between Stanton Harcourt and Standlake, crossing the Windrush at a bridge
that seemed to serve as the meeting point for a great multitude of dog walkers. My geopup, who’s not always the friendliest with new dogs, enjoyed greeting a few of them while warily
watching the others.
We looped around Oxlease Lake in a clockwise direction, crossed Standlake Brook (the dog was very keen to get a drink of water, and in trying to do so made herself exceptionally muddy),
and began working our way up the long driveway past the swimmers and anglers and sailors assembling and preparing for their bank holiday activities. I recalled that I’d been up this way about a year ago to find GCAQJN1 “Hardwick park 1”: I got the FTF on that, but it proved to be a short-lived
cache, getting retired only three or four months later when park owners cut back the trees that had been its host. But I’d actually been here much earlier, too – over a decade ago –
long before I moved to the local area, to find the much-more long-lived GC1TPFY “Constellations 4”. Strange to hunt for
caches in places that I’ve walked past at least twice before, before those caches were hidden!
First up was “Mossy” (GCB61ZC). The dog – who was by now feeling herself again and happy to lead the way – struggled with the narrow kissing-gate to get onto the trail (she’s not so
bright and doesn’t understand that she needs to make room for me to join her before I can open the gate) but soon we were on the path. The hiding place leapt out at me and soon the
cache was in hand, the log signed (right behind Mad H@ter, whose Leafield series I was just attempting five days ago), and the cache returned to its hiding spot beneath its excellent
camoflage. I hope the container survives the winter rains!
Second was “Ivy” (GCAR5HV): a brief walk through the holiday park away (via a glance at the watersports centre, which by the looks of things have paddleboards for rent: I first tried
paddleboarding on the sea and figure it might be easier on a lake, so perhaps I’ll find an excuse to come down here and have a go at some point). The host was easy to find, but it took
some searching to put my hand on the container because I started at the “wrong” side. It looks like it’s had (unlogged?) maintenance done since BusyLittleGeo’s visit last week: the
cache was in perfect condition and the logbook was empty.
Now it was time to return home and give this happy (but mucky) dog a bath. We retraced our steps until Dix Pit, but then cut through the Devils’ Quoits and out through Hayfield Green to
return to Stanton Harcourt, and from there picked our way back through the fields at Sutton to return home.
Y’all seemed to enjoy the “overworld” map I shared the other day, so here’s another “feelie” from my kids’ ongoing D&D campaign.
The party has just arranged for passage aboard a pioneering (and experimental) Elvish airship. Here’s a deck plan (only needs a “you are here” dot!) to help them get their bearings.
In preparation for Family D&D Night (and with thanks to my earlier guide to splicing maps together!), I’ve finally completed an
expanded “overworld” map for our game world. So far, the kids have mostly hung around on the North coast of the Central Sea, but they’re picked up a hook that may take them all the way
across to the other side… and beyond?
Banana for scale.
(If your GMing for kids, you probably already know this, but “feelies” go a long way. All the maps. All the scrolls. Maybe even some props. Go all in. They love it.)
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.
Rarely seen nowadays, these UK road signs were eventually declared “too impolite” and “brusque” and have now almost entirely been replaced with the ones that Brits are familiar with
today, which read “Terribly sorry for the inconvenience, I hope it’s no bother, it’s all our fault really, so sorry, really sorry, sorry, I’ll put the kettle on shall I?”
