Journal tags: ai

August was a month of travels. You can press play on that month’s map to follow the journey.

But check out the map for September too because the travels continue. This time my adventures are confined to Europe.

I’m in Spain. Jessica and I flew into Madrid on Saturday. The next day we took a train ride across the Extremaduran landscape to Cáceres, our home for the week.

This is like the sequel to our Sicilian trip. We’re both working remotely. We just happen to do be doing it from a beautiful old town with amazing cuisine.

We’re in a nice apartment that—crucially—has good WiFi. It’s right on the main square, but it’s remarkably quiet.

There’s a time difference of one hour with Brighton. Fortunately everything in Spain happens at least an hour later than it does at home. Waking up. Lunch. Dinner. Everything is time-shifted so that I’m on the same schedule as my colleagues.

I swear I’m more productive working this way. Maybe it’s the knowledge that tapas of Iberican ham await me after work, but I’m getting a lot done this week.

And when the working week is done, the fun begins. Cáceres is hosting its annual Irish fleadh this weekend.

I’ve always wanted to go to it, but it’s quite a hassle to get here just for a weekend. Combining it with a week of remote work makes it more doable.

I’m already having a really nice time here and the tunes haven’t even started yet.

I got a nice email from someone regarding my recent posts about performance on The Session. They said:

I hope this message finds you well. First and foremost, I want to express how impressed I am with the overall performance of https://thesession.org/. It’s a fantastic resource for music enthusiasts like me.

How nice! I responded, thanking them for the kind words.

They sent a follow-up clarification:

Awesome, anyway there was an issue in my message.

The line ‘It’s a fantastic resource for music enthusiasts like me.’ added by chatGPT and I didn’t notice.

I imagine this is what it feels like when you’re on a phone call with someone and towards the end of the call you hear a distinct flushing sound.

I wrote back and told them about Simon’s rule:

I will not publish anything that takes someone else longer to read than it took me to write.

That just feels so rude!

I think that’s a good rule.

Web Summer Camp in Croatia finished with an interesting discussion. It was labelled a town-hall meeting, but it was more like an Oxford debating club.

Two speakers had two minutes each to speak for or against a particular statement. Their stances were assigned to them so they didn’t necessarily believe what they said.

One of the propositions was something like:

In the future, sustainable design will be as important as UX or performance.

That’s a tough one to argue against! But that’s what Sophia had to do.

She actually made a fairly compelling argument. She said that real impact isn’t going to come from individual websites changing their colour schemes. Real impact is going to come from making server farms run on renewable energy. She advocated for political action to change the system rather than having the responsibility heaped on the shoulders of the individuals making websites.

It’s a fair point. Much like the concept of a personal carbon footprint started life at BP to distract from corporate responsibility, perhaps we’re going to end up navel-gazing into our individual websites when we should be collectively lobbying for real change.

It’s akin to clicktivism—thinking you’re taking action by sharing something on social media, when real action requires hassling your political representative.

I’ve definitely seen some examples of performative sustainability on websites.

For example, at the start of this particular debate at Web Summer Camp we were shown a screenshot of a municipal website that has a toggle. The toggle supposedly enables a low-carbon mode. High resolution images are removed and for some reason the colour scheme goes grayscale. But even if those measures genuinely reduced energy consumption, it’s a bit late to enact them only after the toggle has been activated. Those hi-res images have already been downloaded by then.

Defaults matter. To be truly effective, the toggle needs to work the other way. Start in low-carbon mode, and only download the hi-res images when someone specifically requests them. (Hopefully browsers will implement prefers-reduced-data soon so that we can have our sustainable cake and eat it.)

Likewise I’ve seen statistics bandied about around the energy-savings that could be made if we used dark colour schemes. I’m sure the statistics are correct, but I’d like to see them presented side-by-side with, say, the energy impact of Google Tag Manager or React or any other wasteful dependencies that impact performance invisibly.

That’s the crux. Most of the important work around energy usage on websites is invisible. It’s the work done to not add more images, more JavaScript or more web fonts.

And it’s not just performance. I feel like the more important the work, the more likely it is to be invisible: privacy, security, accessibility …those matter enormously but you can’t see when a website is secure, or accessible, or not tracking you.

I suspect this is why those areas are all frustratingly under-resourced. Why pour time and effort into something you can’t point at?

Now that I think about it, this could explain the rise of web accessibility overlays. If you do the real work of actually making a website accessible, your work will be invisible. But if you slap an overlay on your website, it looks like you’re making a statement about how much you care about accessibility (even though the overlay is total shit and does more harm than good).

I suspect there might be a similar mindset at work when it comes to interface toggles for low-carbon mode. It might make you feel good. It might make you look good. But it’s a poor substitute for making your website carbon-neutral by default.

He drew a deep breath. ‘Well, I’m back,’ he said.

I know how you feel, Samwise Gamgee.

I have returned from my travels—a week aboard the Queen Mary 2 crossing the Atlantic, followed by a weekend in New York, finishing with a week in Saint Augustine, Florida.

The Atlantic crossing was just as much fun as last time. In fact it was better because this time Jessica and I got to share the experience with our dear friends Dan and Sue.

There was dressing up! There was precarious ballet! There were waves! There were even some dolphins!

The truth is that this kind of Atlantic crossing is a bit like cosplaying a former age of travel. You get out of it what you put it into it. If you’re into LARPing as an Edwardian-era traveller, you’re going to have a good time.

We got very into it. Dressing up for dinner. Putting on a tux for the gala night. Donning masks for the masquerade evening.

It’s actually quite a practical way of travelling if you don’t mind being cut off from all digital communication for a week (this is a feature, not a bug). You adjust your clock by one hour most nights so that by the time you show up in New York, you’re on the right timezone with zero jetlag.

That was just as well because we had a packed weekend of activities in New York. By pure coincidence, two separate groups of friends were also in town from far away. We all met up and had a grand old time. Brunch in Tribeca; a John Cale concert in Prospect Park; the farmer’s market in Union Square; walking the high line …good times with good friends.

New York was hot, but not as hot as what followed in Florida. A week lazing about on Saint Augustine beach. I ate shrimp every single day. I regret nothing.

We timed our exit just right. We flew out of Florida before the tropical storm hit. Then we landed in Gatwick right before the air-traffic control chaos erupted.

I had one day of rest before going back to work.

Well, I say “work”, but the first item in my calendar was speaking at Web Summer Camp in Croatia. Back to the airport.

The talk went well, and I got to attend a performance workshop by Harry. But best of all was the location. Opatija is an idyllic paradise. Imagine crossing a web conference with White Lotus, but in a good way. It felt like a continuation of Florida, but with more placid clear waters.

But now I’m really back. And fortunately the English weather is playing along by being unseasonably warm . It’s as if the warm temperatures are following me around. I like it.

I just described prototype code as code to be thrown away. On that topic…

I’ve been observing how people are programming with large language models and I’ve seen a few trends.

The first thing that just about everyone agrees on is that the code produced by a generative tool is not fit for public consumption. At least not straight away. It definitely needs to be checked and tested. If you enjoy debugging and doing code reviews, this might be right up your street.

The other option is to not use these tools for production code at all. Instead use them for throwaway code. That could be prototyping. But it could also be the code for those annoying admin tasks that you don’t do very often.

Take content migration. Say you need to grab a data dump, do some operations on the data to transform it in some way, and then pipe the results into a new content management system.

That’s almost certainly something you’d want to automate with bespoke code. Once the content migration is done, the code can be thrown away.

Read Matt’s account of coding up his Braggoscope. The code needed to spider a thousand web pages, extract data from those pages, find similarities, and output the newly-structured data in a different format.

I’ve noticed that these are just the kind of tasks that large language models are pretty good at. In effect you’re training the tool on your own very specific data and getting it to do your drudge work for you.

To me, it feels right that the usefulness happens on your own machine. You don’t put the machine-generated code in front of other humans.

Back when the web was young, it wasn’t yet clear what the rules were. Like, could you really just link to something without asking permission?

Then came some legal rulings to establish that, yes, on the web you can just link to anything without checking if it’s okay first.

What about search engines and directories? Technically they’re rifling through all the stuff we publish and reposting snippets of it. Is that okay?

Again, through some legal precedents—but mostly common agreement—everyone decided that on balance it was fine. After all, those snippets they publish are helping your site get traffic.

In short order, search came to rule the web. And Google came to rule search.

The mutually beneficial arrangement persisted uneasily. Despite Google’s search results pages getting worse and worse in recent years, the company’s huge market share of search means you generally want to be in their good books.

Google’s business model relies on us publishing web pages so that they can put ads around the search results linking to that content, and we rely on Google to send people to our websites by responding smartly to search queries.

That has now changed. Instead of responding to search queries by linking to the web pages we’ve made, Google is instead generating dodgy summaries rife with hallucina… lies (a psychic hotline, basically).

Google still benefits from us publishing web pages. We no longer benefit from Google slurping up those web pages.

With AI, tech has broken the web’s social contract:

Google has steadily been manoeuvring their search engine results to more and more replace the pages in the results.

As Chris puts it:

Me, I just think it’s fuckin’ rude.

Google is a portal to the web. Google is an amazing tool for finding relevant websites to go to. That was useful when it was made, and it’s nothing but grown in usefulness. Google should be encouraging and fighting for the open web. But now they’re like, actually we’re just going to suck up your website, put it in a blender with all other websites, and spit out word smoothies for people instead of sending them to your website. Instead.

Ben proposes an update to robots.txt that would allow us to specify licensing information:

Robots.txt needs an update for the 2020s. Instead of just saying what content can be indexed, it should also grant rights.

Like crawl my site only to provide search results not train your LLM.

It’s a solid proposal. But Google has absolutely no incentive to implement it. They hold all the power.

Or do they?

There is still the nuclear option in robots.txt:

User-agent: Googlebot
Disallow: /

That’s what Vasilis is doing:

I have been looking for ways to not allow companies to use my stuff without asking, and so far I coulnd’t find any. But since this policy change I realised that there is a simple one: block google’s bots from visiting your website.

The general consensus is that this is nuts. “If you don’t appear in Google’s results, you might as well not be on the web!” is the common cry.

I’m not so sure. At least when it comes to personal websites, search isn’t how people get to your site. They get to your site from RSS, newsletters, links shared on social media or on Slack.

And isn’t it an uncomfortable feeling to think that there’s a third party service that you absolutely must appease? It’s the same kind of justification used by people who are still on Twitter even though it’s now a right-wing transphobic cesspit. “If I’m not on Twitter, I might as well not be on the web!”

The situation with Google reminds me of what Robin said about Twitter:

The speed with which Twitter recedes in your mind will shock you. Like a demon from a folktale, the kind that only gains power when you invite it into your home, the platform melts like mist when that invitation is rescinded.

We can rescind our invitation to Google.

When I was hosting the DIBI conference in Edinburgh back in May, I moderated an impromptu panel on AI:

On the whole, it stayed quite grounded and mercifully free of hyperbole. Both speakers were treating the current crop of technologies as tools. Everyone agreed we were on the hype cycle, probably the peak of inflated expectations, looking forward to reaching the plateau of productivity.

Something else that happened at that event was that I met Deborah Dawton from the Design Business Association. She must’ve liked the cut of my jib because she invited me to come and speak at their get-together in Brighton on the topic of “AI, Web3 and design.”

The representative from the DBA who contacted me knew what they were letting themselves in for. They wrote:

I’ve read a few of your posts on the subject and it would be great if you could join us to share your perspectives.

How could I say no?

I’ve published a transcript of the short talk I gave.

Today was a good day. The weather was beautiful.

Jessica and I did a little bit of work in the garden—nothing too sweaty. Then Jessica cut my hair. It looks good. And it feels good to have my neck freed up.

We went for a Sunday roast at the nearest pub, which does a most excellent carvery. It was tasty and plentiful so after strolling home, I wanted to do nothing more than sit around.

I sat outside in the back garden under the dappled shade offered by the overhanging trees. I had a good book. I had my mandolin to hand. I’d reach for it occassionally to play a tune or two.

Coco the cat—not our cat—sat nearby, stretching her paws out lazily in the warm muggy air.

It was a good day.

It all started with a trip into the countryside one Sunday a few weeks back.

The weather has been getting better and better. The countryside was calling. Meanwhile, Jessica was getting worried about her newly-acquired driving skills getting rusty. She has her license, but doesn’t get the chance to drive very often. She signed up to a car club that lets her book a hybrid car for a few hours at a time—just enough to keep in practice, and also just enough for a little jaunt into the countryside.

We went for Sunday lunch at the Shepherd and Dog in Fulking, near to Devil’s Dyke (I swear that sentence makes sense if you live ’round these parts). It was a lovely day. The Sunday roast was good. But it was on the way back that things started to go wrong.

We had noticed that one of the front tyres was looking a little flat so we planned to stop into a garage to get that seen to. We never made it that far. The tell-tale rhythmic sounds of rubber flapping around told us that we now had a completely flat tyre. Cue panic.

Fortunately we weren’t too far from a layby. We pulled in on the side of the busy road that runs by Saddlescombe Farm.

This is when the Kafkaesque portion of the day began. Jessica had to call the car club, but reception was spotty to put it mildly. There was much frustration, repitition, and hold music.

Eventually it was sorted out enough that we were told to wait for someone from the AA who’d come by and change the tyre in a few hours. To be fair, there are worse places to be stuck on a sunny Summer’s day. We locked the car and walked off across the rolling hills to pass the time.

The guy from the AA actually showed up earlier than expected. We hurried back and then sat and watched as he did his mechanical mending. We got the all-clear to drive the car back to Brighton, as long we didn’t exceed 50 miles per hour.

By the time we got home, we were beat. What a day! I could feel the beginnings of a headache so I popped some ibuprofin to stave it off. Neither of us could be bothered cooking, so we opted for a lazy evening in front of the telly eating takeaway.

I went onto Deliveroo and realised I couldn’t even manage the cognitive overhead of deciding what to eat. So I just went to my last order—a nice mix of Chinese food—and clicked on the option to place exactly the same order again.

And so we spent our Sunday evening munching on Singapore fried noodles and catching up on the most excellent Aussie comedy series, Colin From Accounts. It was just what I needed after an eventful day.

I had just finished my last bite when I felt I needed to cough. That kicked off some wheezing. That was a bit weird. So was the itchy sensation in my ears. Like, the insides of my ears were itchy. Come to think of it, my back was feeling really itchy too.

The wheeziness was getting worse. I had been trying to pass it off, responding to Jessica’s increasingly worried questions with “I’m grand, I’ll be f…” Sorry, had to cough. Trying to clear my throat. It feels a bit constricted.

When Jessica asked if she should call 111, I nodded. Talking took a bit of effort.

Jessica described my symptoms over the phone. Then the operator asked to speak to me. I answered the same questions, but in a much wheezier way.

An ambulance was on its way. But if the symptoms got worse, we should call 999.

The symptoms got worse. Jessica called 999. The ambulance arrived within minues.

The two paramedics, Alastair and Lucy, set to work diagnosing the problem. Let’s go into the ambulance, they said. They strapped a nebuliser onto my face which made breathing easier. It also made everything I said sound like a pronouncement from Bane.

They were pretty sure it was anaphylaxis. I’ve never been allergic to anything in my life, but clearly I was reacting to something. Was it something in the Chinese food? Something in the countryside?

In any case, they gave me a jab of antihistamine into my arm and took us to the emergency room.

By the time we got there, I was feeling much better. But they still needed to keep me under observation. So Jessica and I spent a few hours sitting in the hallway. Someone came by every now and then to check on me and offer us some very welcome cups of tea.

Once it was clear that I was fully recovered, I was discharged with a prescription for an EpiPen.

I picked up the prescription the next day. Having an EpiPen filled with adrenaline was reassuring but it was disconcerting not knowing what caused my anaphylactic reaction in the first place.

After that stressful weekend, life went back to normal, but with this cloud of uncertainty hovering above. Was that it? Would it happen again? Why did it happen?

The weather stayed nice all week. By the time the next weekend rolled around, I planned to spend it doing absolutely nothing. That was just as well, because when I woke up on Saturday morning, I had somehow managed to twist something in my shoulder. I guess I’m at that age now where I can injure myself in my sleep.

I took some neproxin, which helped. After a while, the pain was gone completely.

Jessica and I strolled to the park and had brunch in a nice local café. Then we strolled home and sat out in the garden, enjoying the sunshine.

I was sitting there reading my book when I noticed it. The insides of my ears. They were getting itchy. I swallowed nervously. Was it my imagination or did that swallowing sensation feel slightly constricted. And is that a wheeze I hear?

It was happening again.

The symptoms continued to get worse. Alright, it was time to use that EpiPen. I had read the instructions carefully so I knew just what to do. I did the EpiPen mambo: hold, jab, press.

It worked. We called 999 (as instructed) and were told to go the emergency room. This time we went by taxi.

I checked in, and then sat in the waiting room. I noticed that everyone else had white wristbands, but mine was red. I guess my place in the triage was high priority.

As I sat there, I could feel some of those symptoms returning, but very slowly. By the time we saw someone, there was no mistaking it. The symptoms were coming back.

I was hooked up to the usual instruments—blood pressure, heart rate, blood oxygen—while the hospital staff conferred about what to do. I was getting a bit clammy. I started to feel a bit out of it.

Beep, beep! One of those numbers—blood oxygen?—had gone below a safe threshold. I saw the staff go into action mode. Someone hit a button—the red light in the ceiling started flashing. Staff who had been dealing with other patients came to me.

Instructions were spoken clearly and efficiently, then repeated back with equal clarity and efficiency. “Adrenaline. One in ten thousand.” “Adrenaline. One in ten thousand.” They reclined my chair, elevated my legs, pulled down my trousers, and gave me my second shot in one day.

It worked. I started to feel much better straight away. But once again, I needed to be kept under observation. I was moved to the “recus” ward, passing through the corridor that was so familiar from the previous weekend.

This time we’d spend a grand total of twelve hours in the hospital. Once again, it was mercifully uneventful. But it gave us the opportunity to put two and two together. What was the common thread between both episodes?

Ibuprofin. Neproxin. They’re both non-steroidal anti-inflammatory drugs (NSAIDS). That fits

Foods are the most common trigger in children and young adults, while medications and insect bites and stings are more common in older adults. … Any medication may potentially trigger anaphylaxis. The most common are β-lactam antibiotics (such as penicillin) followed by aspirin and NSAIDs.

The doctors agreed—the connection looked pretty clear. I saw my GP a few days later and she’s reffered me to an allergy-testing clinic to confirm it. That might take a while though. In the meantime, I also got another prescription for more EpiPens.

Hopefully I won’t need them. I’m very, very glad that I don’t appear to be allergic to a foodstuff. I’d rather do without ibuprofin and aspirin than have to vigilantly monitor my diet.

But I do need to get into the habit of making sure I’ve got at least one EpiPen with me wherever I go. I’ll probably never need to use it. I feel like I’ve had enough anaphylaxis in the past couple of weeks to last me a lifetime.

Oh, and one more thing. I know everyone says this after dealing with some kind of health emergency in this country, but I’m going to say it anyway:

The NHS is easily the best thing ever invented in the UK. Everyone I dealt with was fantastic. It was all in a day’s work for them, but I am forever in their debt (whereas had this happened in, say, the USA, I would forever be in a much more literal debt).

Thank you, NHS!

I’m sure you’ve heard the law of the instrument: when all you have is a hammer, everything looks like a nail.

There’s another side to it. If you’re selling hammers, you’ll depict a world full of nails.

Recent hammers include cryptobollocks and virtual reality. It wasn’t enough for blockchains and the metaverse to be potentially useful for some situations; they staked their reputations on being utterly transformative, disrupting absolutely every facet of life.

This kind of hype is a terrible strategy in the long-term. But if you can convince enough people in the short term, you can make a killing on the stock market. In truth, the technology itself is superfluous. It’s the hype that matters. And if the hype is over-inflated enough, you can even get your critics to do your work for you, broadcasting their fears about these supposedly world-changing technologies.

You’d think we’d learn. If an industry cries wolf enough times, surely we’d become less trusting of extraordinary claims. But the tech industry continues to cry wolf—or rather, “hammer!”—at regular intervals.

The latest hammer is machine learning, usually—incorrectly—referred to as Artificial Intelligence. What makes this hype cycle particularly infuriating is that there are genuine use cases. There are some nails for this hammer. They’re just not as plentiful as the breathless hype—both positive and negative—would have you believe.

When I was hosting the DiBi conference last week, there was a little section on generative “AI” tools. Matt Garbutt covered the visual side, demoing tools like Midjourney. Scott Salisbury covered the text side, showing how you can generate code. Afterwards we had a panel discussion.

During the panel I asked some fairly straightforward questions that nobody could answer. Who owns the input (the data used by these generative tools)? Who owns the output?

On the whole, it stayed quite grounded and mercifully free of hyperbole. Both speakers were treating the current crop of technologies as tools. Everyone agreed we were on the hype cycle, probably the peak of inflated expectations, looking forward to reaching the plateau of productivity.

Scott explicitly warned people off using generative tools for production code. His advice was to stick to side projects for now.

Matt took a closer look at where these tools could fit into your day-to-day design work. Mostly it was pretty sensible, except when he suggested that there could be any merit to using these tools as a replacement for user testing. That’s a terrible idea. A classic hammer/nail mismatch.

I think I moderated the panel reasonably well, but I have one regret. I wish I had first read Baldur Bjarnason’s new book, The Intelligence Illusion. I started reading it on the train journey back from Edinburgh but it would have been perfect for the panel.

The Intelligence Illusion is very level-headed. It is neither pro- nor anti-AI. Instead it takes a pragmatic look at both the benefits and the risks of using these tools in your business.

It has excellent advice for spotting genuine nails. For example:

Generative AI has impressive capabilities for converting and modifying seemingly unstructured data, such as prose, images, and audio. Using these tools for this purpose has less copyright risk, fewer legal risks, and is less error prone than using it to generate original output.

Think about transcripts of videos or podcasts—an excellent use of this technology. As Baldur puts it:

The safest and, probably, the most productive way to use generative AI is to not use it as generative AI. Instead, use it to explain, convert, or modify.

He also says:

Prefer internal tools over externally-facing chatbots.

That chimes with what I’ve been seeing. The most interesting uses of this technology that I’ve seen involve a constrained dataset. Like the way Luke trained a language model on his own content to create a useful chat interface.

Anyway, The Intelligence Illusion is full of practical down-to-earth advice based on plenty of research backed up with copious citations. I’m only halfway through it and it’s already helped me separate the hype from the reality.

Web performance is an unalloyed good. No one has ever complained that a website is too fast.

So the benefit is pretty obvious. Users like fast websites. But there are other benefits to web performance. And they don’t all get equal airtime.

Business

A lot of good web performance practices come down to the first half of Postel’s Law: be conservative in what send. Images, fonts, JavaScript …remove what you don’t need and optimise the hell out of what’s left.

That can translate to savings. If you’re paying for the bandwidth every time a hefty file is downloaded, your monthly bill could get pretty big.

So apart from the indirect business benefits of happy users converting to happy customers, there can be a real nuts’n’bolts bottom-line saving to be made by having a snappy website.

Sustainability

This is related to the cost-savings benefit. If you’re shipping less stuff down the wire, and you’re optimising what you do send, then there’s less energy required.

Whether less energy directly translates to a smaller carbon footprint depends on how the energy is being generated. If your servers are running on 100% renewable energy sources, then reducing the output of your responses won’t reduce your carbon footprint.

But there’s an energy cost at the other end too. Think of all the devices making requests to your server. If you’re making those devices work hard—by downloading, parsing, executing lots of JavaScript, for example—then you’re draining battery life. And you can’t guarantee that the battery will be replenished from renewable energy sources.

That’s why sites like the website carbon calculator have so much crossover with web performance:

From data centres to transmission networks to the billions of connected devices that we hold in our hands, it is all consuming electricity, and in turn producing carbon emissions equal to or greater than the global aviation industry. Yikes!

Inclusivity

There comes a point when a slow website isn’t just inconvenient, it’s inaccessible.

I’ve always liked the German phrase for accessible: barrierefrei—free of barriers. With every file you add to a website’s dependencies, you’re adding one more barrier. Eventually the barrier is insurmountable for people with older devices or slower internet connections. If they can no longer access your website, your website is quite literally inaccessible.

Making the case

I’ve noticed that when it comes to making the argument in favour of better web performance, people often default to the business benefits.

I get it. We’re always being told to speak the language of business. The psychology seems pretty straightforward; if you think that the people you’re trying to convince are mostly concerned with the bottom line, use the language of commerce to change their minds.

But that’s always felt reductive to me.

Sure, those people almost certainly do care about the business. Who doesn’t? But they’re also humans. I feel like if really want to convince them, speak to their hearts. Show them the bigger picture.

Eliel Saarinen said:

Always design a thing by considering it in its next larger context; a chair in a room, a room in a house, a house in an environment, an environment in a city plan.

I think the same could apply to making the case for web performance. Don’t stop at the obvious benefits. Go wider. Show the big-picture implications.

Robin penned a little love letter to the details element. I agree. It is a joyous piece of declarative power.

That said, don’t go overboard with it. It’s not a drop-in replacement for more complex widgets. But it is a handy encapsulation of straightforward progressive disclosure.

Just last week I added a couple of more details elements to The Session …kind of. There’s a bit of server-side conditional logic involved to determine whether details is the right element.

When you’re looking at a tune, one of the pieces of information you see is how many recordings there of that tune. Now if there are a lot of recordings, then there’s some additional information about which other tunes this one gets recorded with. That information is extra. Mere details, if you will.

You can see it in action on this tune listing. Thanks to the details element, the extra information is available to those who want it, but by default that information is tucked away—very handy for not clogging up that part of the page.

<details>
<summary>There are 181 recordings of this tune.</summary>
This tune has been recorded together with
<ul>
<li>…</li>
<li>…</li>
<li>…</li>
</ul>
</details>

Likewise, each tune page includes any aliases for the tune (in Irish music, the same tune can have many different titles—and the same title can be attached to many different tunes). If a tune has just a handful of aliases, they’re displayed in situ. But once you start listing out more than twenty names, it gets overwhelming.

The details element rides to the rescue once again.

Compare the tune I mentioned above, which only has a few aliases, to another tune that is known by many names.

Again, the main gist is immediately available to everyone—how many aliases are there? But if you want to go through them all, you can toggle that details element open.

You can effectively think of the summary element as the TL;DR of HTML.

<details>
<summary>There are 31 other names for this tune.</summary>
<p>Also known as…</p>
</details>

There’s another classic use of the details element: frequently asked questions. In the case of The Session, I’ve marked up the house rules and FAQs inside details elements, with the rule or question as the summary.

But there’s one house rule that’s most important (“Be civil”) so that details element gets an additional open attribute.

<details open>
<summary>Be civil</summary>
<p>Contributions should be constructive and polite, not mean-spirited or contributed with the intention of causing trouble.</p>
</details>

I woke up today to a very annoying new bug in Firefox. The browser shits the bed in an unpredictable fashion when rounding up single pixel line widths in SVG. That’s quite a problem on The Session where all the sheet music is rendered in SVG. Those thin lines in sheet music are kind of important.

Browser bugs like these are very frustrating. There’s nothing you can do from your side other than filing a bug. The locus of control is very much with the developers of the browser.

Still, the occasional regression in a browser is a price I’m willing to pay for a plurality of rendering engines. Call me old-fashioned but I still value the ecological impact of browser diversity.

That said, I understand the argument for converging on a single rendering engine. I don’t agree with it but I understand it. It’s like this…

Back in the bad old days of the original browser wars, the browser companies just made shit up. That made life a misery for web developers. The Web Standards Project knocked some heads together. Netscape and Microsoft would agree to support standards.

So that’s where the bar was set: browsers agreed to work to the same standards, but competed by having different rendering engines.

There’s an argument to be made for raising that bar: browsers agree to work to the same standards, and have the same shared rendering engine, but compete by innovating in all other areas—the browser chrome, personalisation, privacy, and so on.

Like I said, I understand the argument. I just don’t agree with it.

One reason for zeroing in a single rendering engine is that it’s just too damned hard to create or maintain an entirely different rendering engine now that web standards are incredibly powerful and complex. Only a very large company with very deep pockets can hope to be a rendering engine player. Google. Apple. Heck, even Microsoft threw in the towel and abandoned their rendering engine in favour of Blink and V8.

And yet. Andreas Kling recently wrote about the Ladybird browser. How we’re building a browser when it’s supposed to be impossible:

The ECMAScript, HTML, and CSS specifications today are (for the most part) stellar technical documents whose algorithms can be implemented with considerably less effort and guesswork than in the past.

I’ll be watching that project with interest. Not because I plan to use the brower. I’d just like to see some evidence against the complexity argument.

Meanwhile most other browser projects are building on the raised bar of a shared browser engine. Blisk, Brave, and Arc all use Chromium under the hood.

Arc is the most interesting one. Built by the wonderfully named Browser Company of New York, it’s attempting to inject some fresh thinking into everything outside of the rendering engine.

Experiments like Arc feel like they could have more in common with tools-for-thought software like Obsidian and Roam Research. Those tools build knowledge graphs of connected nodes. A kind of hypertext of ideas. But we’ve already got hypertext tools we use every day: web browsers. It’s just that they don’t do much with the accumulated knowledge of our web browsing. Our browsing history is a boring reverse chronological list instead of a cool-looking knowledge graph or timeline.

For inspiration we can go all the way back to Vannevar Bush’s genuinely seminal 1945 article, As We May Think. Bush imagined device, the Memex, was a direct inspiration on Douglas Engelbart, Ted Nelson, and Tim Berners-Lee.

The article describes a kind of hypertext machine that worked with microfilm. Thanks to Tim Berners-Lee’s World Wide Web, we now have a global digital hypertext system that we access every day through our browsers.

But the article also described the idea of “associative trails”:

Wholly new forms of encyclopedias will appear, ready made with a mesh of associative trails running through them, ready to be dropped into the memex and there amplified.

Our browsing histories are a kind of associative trail. They’re as unique as fingerprints. Even if everyone in the world started on the same URL, our browsing histories would quickly diverge.

Bush imagined that these associative trails could be shared:

The lawyer has at his touch the associated opinions and decisions of his whole experience, and of the experience of friends and authorities.

Heck, making a useful browsing history could be a real skill:

There is a new profession of trail blazers, those who find delight in the task of establishing useful trails through the enormous mass of the common record.

Taking something personal and making it public isn’t a new idea. It was what drove the wave of web 2.0 startups. Before Flickr, your photos were private. Before Delicous, your bookmarks were private. Before Last.fm, what music you were listening to was private.

I’m not saying that we should all make our browsing histories public. That would be a security nightmare. But I am saying there’s a lot of untapped potential in our browsing histories.

Let’s say we keep our browsing histories private, but make better use of them.

From what I’ve seen of large language model tools, the people getting most use of out of them are training them on a specific corpus. Like, “take this book and then answer my questions about the characters and plot” or “take this codebase and then answer my questions about the code.” If you treat these chatbots as calculators for words they can be useful for some tasks.

Large language model tools are getting smaller and more portable. It’s not hard to imagine one getting bundled into a web browser. It feeds on your browsing history. The bigger your browsing history, the more useful it can be.

Except, y’know, for the times when it just make shit up.

Vannevar Bush didn’t predict a Memex that would hallucinate bits of microfilm that didn’t exist.

Picture someone tediously going through a spreadsheet that someone else has filled in by hand and finding yet another error.

“I wish to God these calculations had been executed by steam!” they cry.

The year was 1821 and technically the spreadsheet was a book of logarithmic tables. The frustrated cry came from Charles Babbage, who channeled his frustration into a scheme to create the world’s first computer.

His difference engine didn’t work out. Neither did his analytical engine. He’d spend his later years taking his frustrations out on street musicians, which—as a former busker myself—earns him a hairy eyeball from me.

But we’ve all been there, right? Some tedious task that feels soul-destroying in its monotony. Surely this is exactly what machines should be doing?

I have a hunch that this is where machine learning and large language models might turn out to be most useful. Not in creating breathtaking works of creativity, but in menial tasks that nobody enjoys.

Someone was telling me earlier today about how they took a bunch of haphazard notes in a client meeting. When the meeting was done, they needed to organise those notes into a coherent summary. Boring! But ChatGPT handled it just fine.

I don’t think that use-case is going to appear on the cover of Wired magazine anytime soon but it might be a truer glimpse of the future than any of the breathless claims being eagerly bandied about in Silicon Valley.

You know the way we no longer remember phone numbers, because, well, why would we now that we have machines to remember them for us? I’d be quite happy if machines did that for the annoying little repetitive tasks that nobody enjoys.

I’ll give you an example based on my own experience.

Regular expressions are my kryptonite. I’m rubbish at them. Any time I have to figure one out, the knowledge seeps out of my brain before long. I think that’s because I kind of resent having to internalise that knowledge. It doesn’t feel like something a human should have to know. “I wish to God these regular expressions had been calculated by steam!”

Now I can get a chatbot with a large language model to write the regular expression for me. I still need to describe what I want, so I need to write the instructions clearly. But all the gobbledygook that I’m writing for a machine now gets written by a machine. That seems fair.

Mind you, I wouldn’t blindly trust the output. I’d take that regular expression and run it through a chatbot, maybe a different chatbot running on a different large language model. “Explain what this regular expression does,” would be my prompt. If my input into the first chatbot matches the output of the second, I’d have some confidence in using the regular expression.

A friend of mine told me about using a large language model to help write SQL statements. He described his database structure to the chatbot, and then described what he wanted to select.

Again, I wouldn’t use that output without checking it first. But again, I might use another chatbot to do that checking. “Explain what this SQL statement does.”

Playing chatbots off against each other like this is kinda how machine learning works under the hood: generative adverserial networks.

Of course, the task of having to validate the output of a chatbot by checking it with another chatbot could get quite tedious. “I wish to God these large language model outputs had been validated by steam!”

Sounds like a job for machines.

You know how when you’re on hold to any customer service line you hear a message that thanks you for calling and claims your call is important to them. The message always includes a disclaimer about calls possibly being recorded “for training purposes.”

Nobody expects that any training is ever actually going to happen—surely we would see some improvement if that kind of iterative feedback loop were actually in place. But we most certainly want to know that a call might be recorded. Recording a call without disclosure would be unethical and illegal.

Consider chatbots.

If you’re having a text-based (or maybe even voice-based) interaction with a customer service representative that doesn’t disclose its output is the result of large language models, that too would be unethical. But, at the present moment in time, it would be perfectly legal.

That needs to change.

I suspect the necessary legislation will pass in Europe first. We’ll see if the USA follows.

In a way, this goes back to my obsession with seamful design. With something as inherently varied as the output of large language models, it’s vital that people have some way of evaluating what they’re told. I believe we should be able to see as much of the plumbing as possible.

The bare minimum amount of transparency is revealing that a machine is in the loop.

This shouldn’t be a controversial take. But I guarantee we’ll see resistance from tech companies trying to sell their “AI” tools as seamless, indistinguishable drop-in replacements for human workers.

The last talk at the last dConstruct was by local clever clogs Anil Seth. It was called Your Brain Hallucinates Your Conscious Reality. It’s well worth a listen.

Anil covers a lot of the same ground in his excellent book, Being You. He describes a model of consciousness that inverts our intuitive understanding.

We tend to think of our day-to-day reality in a fairly mechanical cybernetic manner; we receive inputs through our senses and then make decisions about reality informed by those inputs.

As another former dConstruct speaker, Adam Buxton, puts it in his interview with Anil, it feels like that old Beano cartoon, the Numskulls, with little decision-making homonculi inside our head.

But Anil posits that it works the other way around. We make a best guess of what the current state of reality is, and then we receive inputs from our senses, and then we adjust our model accordingly. There’s still a feedback loop, but cause and effect are flipped. First we predict or guess what’s happening, then we receive information. Rinse and repeat.

The book goes further and applies this to our very sense of self. We make a best guess of our sense of self and then adjust that model constantly based on our experiences.

There’s a natural tendency for us to balk at this proposition because it doesn’t seem rational. The rational model would be to make informed calculations based on available data …like computers do.

Maybe that’s what sets us apart from computers. Computers can make decisions based on data. But we can make guesses.

Enter machine learning and large language models. Now, for the first time, it appears that computers can make guesses.

The guess-making is not at all like what our brains do—large language models require enormous amounts of inputs before they can make a single guess—but still, this should be the breakthrough to be shouted from the rooftops: we’ve taught machines how to guess!

And yet. Almost every breathless press release touting some revitalised service that uses AI talks instead about accuracy. It would be far more honest to tout the really exceptional new feature: imagination.

Using AI, we will guess who should get a mortgage.

Using AI, we will guess who should get hired.

Using AI, we will guess who should get a strict prison sentence.

Reframed like that, it’s easy to see why technologists want to bury the lede.

Alas, this means that large language models are being put to use for exactly the wrong kind of scenarios.

(This, by the way, is also true of immersive “virtual reality” environments. Instead of trying to accurately recreate real-world places like meeting rooms, we should be leaning into the hallucinatory power of a technology that can generate dream-like situations where the pleasure comes from relinquishing control.)

Take search engines. They’re based entirely on trust and accuracy. Introducing a chatbot that confidentally conflates truth and fiction doesn’t bode well for the long-term reputation of that service.

But what if this is an interface problem?

Currently facts and guesses are presented with equal confidence, hence the accurate descriptions of the outputs as bullshit or mansplaining as a service.

What if the more fanciful guesses were marked as such?

As it is, there’s a “temperature” control that can be adjusted when generating these outputs; the more the dial is cranked, the further the outputs will stray from the safest predictions. What if that could be reflected in the output?

I don’t know what that would look like. It could be typographic—some markers to indicate which bits should be taken with pinches of salt. Or it could be through content design—phrases like “Perhaps…”, “Maybe…” or “It’s possible but unlikely that…”

I’m sure you’ve seen the outputs when people request that ChatGPT write their biography. Perfectly accurate statements are generated side-by-side with complete fabrications. This reinforces our scepticism of these tools. But imagine how differently the fabrications would read if they were preceded by some simple caveats.

A little bit of programmed humility could go a long way.

Right now, these chatbots are attempting to appear seamless. If 80% or 90% of their output is accurate, then blustering through the other 10% or 20% should be fine, right? But I think the experience for the end user would be immensely more empowering if these chatbots were designed seamfully. Expose the wires. Show the workings-out.

Mind you, that only works if there is some way to distinguish between fact and fabrication. If there’s no way to tell how much guessing is happening, then that’s a major problem. If you can’t tell me whether something is 50% true or 75% true or 25% true, then the only rational response is to treat the entire output as suspect.

I think there’s a fundamental misunderstanding behind the design of these chatbots that goes all the way back to the Turing test. There’s this idea that the way to make a chatbot believable and trustworthy is to make it appear human, attempting to hide the gears of the machine. But the real way to gain trust is through honesty.

I want a machine to tell me when it’s guessing. That won’t make me trust it less. Quite the opposite.

After all, to guess is human.

We use metaphors all the time. To quote George Lakoff, we live by them.

We use analogies some of the time. They’re particularly useful when we’re wrapping our heads around something new. By comparing something novel to something familiar, we can make a shortcut to comprehension, or at least, categorisation.

But we need a certain amount of vigilance when it comes to analogies. Just because something is like something else doesn’t mean it’s the same.

With that in mind, here are some ways that people are describing generative machine learning tools. Large language models are like…

• …a blurry JPEG of the web,
• …fly-by-wire avionics,
• …drum machines,
• …an octopus.

I’ve already written about how much I enjoyed hosting Leading Design San Francisco last week.

All the speakers were terrific. Lola’s talk was particularly …um, interesting:

In this talk, Lola will share her adventures in the world of blockchain, the hostility she experienced in her first go-round in 2018, and why she’s chosen to head back to a technology that is going through its largest reputational and social crisis to date.

Wait …I was supposed to stand on stage and introduce a talk that was (at least partly) about blockchain? I have opinions.

As it turned out, Lola warned me that I’d be making an appearance in her talk. She was going to quote that blog post. Before the talk, I asked her how obnoxious I could be about blockchain in her intro. She told me to bring it.

So in the introduction, I deployed all the sarcasm I had in me and said:

Listen, we designers have a tendency to be over-critical of things sometimes. There are all these ideas that we dismiss: phrenology, homeopathy, flat-earthism …blockchain. Haters gonna hate.

I remember somebody asking online a while back, “Why the hate for web3?” And someone I know responded by saying “We hate it because we understand it.” I think there’s a lot of truth to that.

But look, just because blockchains are powering crypto ponzi schemes and N F fucking Ts, it’s worth remembering that it’s also simply a technology. It’s a technological solution in search of a problem.

To be fair, it’s still early days. After all, it’s only been over a decade now.

It’s like the law of instrument says; when all you have is a hammer, everything looks like a nail. Blockchain is like that. Except the hammer is also made of glass.

Anyway, Lola is going to defend the indefensible and talk about blockchain. One thing to keep in mind is this: remember when everyone was talking about “The Cloud”? And then it turned out that you could substitute the phrase “someone else’s server” for “The Cloud?” Well, every time you hear Lola say the word “blockchain”, I’d like you to mentally substitute the phrase “multiple copies of a spreadsheet.”

Please give an open mind and a warm welcome to Lola Oyelayo Pearson!

I got some laughs. I also got lots of gasps and pearl-clutching, as though I were saying something taboo. Welcome to San Francisco.

Lola gave as good as she got. I got a roasting in her talk.

And just to clarify, Lola and I are friends—this was a consensual smackdown.

There was a very serious point to Lola’s talk. Cryptobollocks and other blockchain-powered schemes have historically been very bro-y, and exploitative of non-bro communities. Lola wants to fight that trend.

I get it. But it reminds me a bit of the justifications you hear from people who go to work at Facebook claiming that they can do more good from the inside. Whatever helps you sleep at night.

The crux of Lola’s belief is this: blockchain technology is inevitable, therefore it is uncumbent on us as ethical designers to ensure that the technology is deployed in a way that empowers people instead of exploiting them.

But I take issue with the premise. Blockchain technology is not inevitable. That’s the worst kind of technological determinism. It’s defeatist. It’s a depressing view of “progress” driven not by people, but by technological forces beyond our control.

I refuse to accept that anti-humanist deterministic view.

In any case, for technological determinism to have any validity, there needs to be something to it. At least virtual reality and machine learning are based on some actual technologies. In the case of cryptobollocks, there is no there there. There is nothing except the hype, which is why you’ll see blockchain enthusiasts trying to ride the coattails of trending technologies in a logical fallacy that goes something like this:

1. There are technologies that will be really big in the future,
2. blockchain is a technology, therefore
3. blockchain will be really big in the future.

Blockchain is bullshit. It isn’t even very clever bullshit. And it certainly isn’t inevitable.

I’ve mentioned before that I’m not a fan of initialisms and acronyms. They can be exclusionary.

It bothers me doubly when everyone is talking about AI.

First of all, the term is so vague as to be meaningless. Sometimes—though rarely—AI refers to general artificial intelligence. Sometimes AI refers to machine learning. Sometimes AI refers to large language models. Sometimes AI refers to a series of if/else statements. That’s quite a spectrum of meaning.

Secondly, there’s the assumption that everyone understands the abbreviation. I guess that’s generally a safe assumption, but sometimes AI could refer to something other than artificial intelligence.

In countries with plenty of pastoral agriculture, if someone works in AI, it usually means they’re going from farm to farm either extracting or injecting animal semen. AI stands for artificial insemination.

I think that abbreviation might work better for the kind of things currently described as using AI.

We were discussing this hot topic at work recently. Is AI coming for our jobs? The consensus was maybe, but only the parts of our jobs that we’re more than happy to have automated. Like summarising some some findings. Or perhaps as a kind of lorem ipsum generator. Or for just getting the ball rolling with a design direction. As Terence puts it:

Midjourney is great for a first draft. If, like me, you struggle to give shape to your ideas then it is nothing short of magic. It gets you through the first 90% of the hard work. It’s then up to you to refine things.

That’s pretty much the conclusion we came to in our discussion at Clearleft. There’s no way that we’d use this technology to generate outputs for clients, but we certainly might use it to generate inputs. It’s like how we’d do a quick round of sketching to get a bunch of different ideas out into the open. Terence is spot on when he says:

Midjourney lets me quickly be wrong in an interesting direction.

To put it another way, using a large language model could be a way of artificially injecting some seeds of ideas. Artificial insemination.

So now when I hear people talk about using AI to create images or articles, I don’t get frustrated. Instead I think, “Using artificial insemination to create images or articles? Yes, that sounds about right.”

I shared this link in Slack with my co-workers today:

Cultivating depth and stillness in research by Andy Matuschak.

I wasn’t sure whether it belonged in the #research or the #design channel. While it’s ostensibly about research, I think it applies to design more broadly. Heck, it probably applies to most fields. I should have put it in the Slack channel I created called #iiiiinteresting.

The article is all about that feeling of frustration when things aren’t progressing quickly, even when you know intellectually that not everything should always progress quickly.

The article is filled with advice for battling this feeling, including this observation on curiosity:

Curiosity can also totally change my relationship to setbacks. Say I’ve run an experiment, collected the data, done the analysis, and now I’m writing an essay about what I’ve found. Except, halfway through, I notice that one column of the data really doesn’t support the conclusion I’d drawn. Oops. It’s tempting to treat this development as a frustrating impediment—something to be overcome expediently. Of course, that’s exactly the wrong approach, both emotionally and epistemically. Everything becomes much better when I react from curiosity instead: “Oh, wait, wow! Fascinating! What is happening here? What can this teach me? How might this change what I try next?”

But what really resonated with me was this footnote attached to that paragraph:

I notice that I really struggle to generate curiosity about problems in programming. Maybe it’s because I’ve been doing it so long, but I think it’s because my problems are usually with ephemeral ideas, incidental to what I actually care about. When I’m fighting some godforsaken Javascript build system, I don’t feel even slightly curious to “really” understand those parochial machinations. I know they’re just going to be replaced by some new tool next year.

I feel seen.

I know I’m not alone. I know people who were driven out of front-end development because they felt the unspoken ultimatum was to either become a “full stack” developer or see yourself out.

Remember Chris’s excellent post, The Great Divide? Zach referenced it recently. He wrote:

The question I keep asking though: is the divide borne from a healthy specialization of skills or a symptom of unnecessary tooling complexity?

Mostly I feel sad about the talented people we’ve lost because they felt their front-of-the-front-end work wasn’t valued.

But wait! Can I turn my frown upside down? Can I take Andy Matuschak’s advice and say, “Oh, wait, wow! Fascinating! What is happening here? What can this teach me?”

Here’s one way of squinting at the situation…

There’s an opportunity here. If many people—myself included—feel disheartened and ground down by the amount of time they need to spend dealing with toolchains and build systems, what kind of system would allow us to get on with making websites without having to deal with that stuff?

I’m not proposing that we get rid of these complex toolchains, but I am wondering if there’s a way to make it someone else’s job.

I guess this job is DevOps. In theory it’s a specialised field. In practice everyone adding anything to a codebase partakes in continual partial DevOps because they must understand the toolchains and build processes in order to change one line of HTML.

I’m not saying “Don’t Make Me Think” when it comes to the tooling. I totally get that some working knowledge is probably required. But the ratio has gotten out of whack. You need a lot of working knowledge of the toolchains and build processes.

In fact, that’s mostly what companies hire for these days. If you’re well versed in HTML, CSS, and vanilla JavaScript, but you’re not up to speed on pipelines and frameworks, you’re going to have a hard time.

That doesn’t seem right. We should change it.