Writing

The summer following my high school graduation I decided to embark on a journey of bikepacking from Vienna, down to the south of Croatia. Going nearly 1,000 kilometers from Austria to Croatia Bikepacking feels like something, especially regarding elevation and terrain.

Was it an absolutely fantastic experience? Sure.
Would I do it again? Absolutely.
Was it life changing the way some people portray it? No.

But that’s not something I expected, not why I decided to do this. My motivation came from inside and the idea formed before I even knew that Bikepacking even was a word. As a result of my planning I got and watched a bunch of Instagram videos but those only reinforced myself in wanting to do this.

You can get an article like this one, maybe a little more background checked and neutral, just by asking ChatGPT. Or, better yet, you can ask ChatGPT to summarize this article.

So why read this? And if you don’t read this but use an LLM to summarize, then why should I write it nicely out in the first place. I could just put bullet points up here and it would be easier for both me and the LLM. That’s the shift that we are going through. And I’ve been writing about The Shift for a long time now, but alway only bits and pieces. In this writeup I’ll try to put those together to draw a bigger, personal picture of the future of the web in an LLM focussed world. This is not about zero touch computer interaction or the web for communication or the internet in general – I have my separate thoughts on those topics. This is about howwebsites as we know them might evolve.

People have started noticing a new years back that most sites don’t need fancy layouts and that unnecessary design is often decreasing conversion. I am going to cite a paragraph from an old article of mine –

There’s a million reasons to publish, but they all come down to two things.

One – getting heard, making noise.
Two – making money.

And the internet is a great place for both of those things. As we’re moving away from classic backend-frontend websites towards a future where content is generated by LLMs, we need to make sure both of those things are protected.

Spotify has social features, but they suck. I wonder why don’t they improve those. Being able to send songs to another person’s Play Queue, repost songs, chat with your friends, share photos and moments with music (à la Instagram stories), etc.

Instagram has music features, but they suck. I can’t play a song without wanting to add that to a post or story, I can’t create playlists. I can favorite songs when I see them on a post or story, I can follow artists, etc.

I would have thought that both would be competing in both fields by now. Since this doesn’t seem to be the case, they should allow for deeper integration. I already since last month can add a song in Instagram to my Spotify favs without leaving Instagram, but this integration could go so much deeper.

Agentic coding models and harnesses have become so effective that a large share of new software is now written by agents. For a good reason, it’s faster, code is at times higher quality than if human written, and there are seemingly no downsides. We thought.

But the majority of new Software feels average, in a sense that it feels a like AI slop, instead of software that was created with craft and care. For all that follows here, it’s important to understand, that AI coding produces impeccable results, if done right. But it all comes down to the process. Years ago we used to start at an idea, sketch it out by hand or on a whiteboard, then refine the user experience and exact optics in Figma, then start development. We used to style every button to perfection, manually set border radii to be concentric and look correctly. Things took time and while something taking longer doesn’t mean that it is better, it does usually mean that more thought has had to be put into.

Today, many teams jump directly from idea to their coding agent (Claude Code, Codex). This quickly gets them an MVP, but not something that excites users. There’s this well known saying that getting the last 20% right takes 80% of the work, and here I would say that getting the last 20% right takes 95% of the work. And it’s these 20% that make the difference between AI slop, and a thought out solution.

I wrote about unifying app experiences on mobile a few years ago (before GenUI even was a thing), and I called it Othara. Back then, I thought of it as “forcing developers to use the unified layouts of the OS,” just like I can quickly set up a SwiftUI application that will absolutely feel like an iOS app. But with the rise of AI, it’s actually possible to have the AI generate the user interface on the fly based on templates, better than ever. If every app is the same, built using a set of components and filled with content, then AI could learn how to do things easier and better than it ever could with current systems like Apple’s App Intents.

Why is there a need for apps to look different? Why does WhatsApp have to look different from Messages, or Spotify from Apple Music?

Phones are stagnating. It didn’t feel exciting at all moving from an iPhone SE 2nd gen to an iPhone 16. Imagine how it would’ve felt going from, for example, an iPhone 12 to the 16. OS updates get me excited, but this wasn’t it. I hate every piece of iOS that I use, nothing is working. I used to think this was because I was using an older phone, but no, it’s just the system that is so incredibly bad. How can it be that Apple’s UI is full of little issues, animations missing or gradients being cut off? Apple used to care. That’s what made them unique. How come no QA person cares? Why do I have a list of 10 UI bugs just in the onboarding when you get your iPhone?

We should start applying the KISS (keep it short and simple) principle to websites. A website should only be as complex as it needs to be to complete its mission. And for most cases, simple websites are generally better. That’s the short version.

They load faster. You find what you came for. You read. You click. You buy. As much as page builders try to sell you on unlimited design flexibility, having a more complex design just for the sake of it doesn’t solve anything.

Sometimes you want more on a site than a simple text and some images. You as a user want to feel something. Apple’s product pages do that beautifully. The animations. The scroll effects. It storytelling at its core and a simple text document just wouldn’t cut it, and I see that perspective.

LLMs will substantially change the way we compute, meaning use technology in general. That’s a given fact for me and many others, simply based on the point that current interfaces are built around the idea that only humans can reason and think. Transformers and LLMs change that completely, and this opens up so many new doors as to how humans and technology co-exist. Notice how I didn’t say “humans use technology”, because I would want to move away from the premise of me “using” tech. Things should feel natural, and technology should move in the background.

Because currently, every time I am using my computer, I feel like this can’t be the best way we have to work, and every time I am in public transport and see everyone scrolling on their phones I feel like this can’t be the end of where technology lead us.

There are 2 camps here, about how the computer of the future will look like, and I’ve had a very interesting discussion a few days ago (March 2024). The question is – will everything evolve around a chatbot, or will a chatbot just not play a role at all when it comes to the future of computing? I see both visions, but the second one seems far more innovative. Let me explain.

Artificial intelligence becomes the primary interface through which humans access knowledge and it’s time to rethink how we store information in the first place.

Currently, writing is our most reliable method of recording knowledge. But right now information goes from

The result? The article itself is never touched. And this needs to be acknowledged and addressed by a frontend-less web.