All Publications by Numeric Citizen

The New Apple Finally Begins to Emerge — Parker Ortolani

Molly Anderson’s already proven herself to be an incredibly talented industrial designer, and if the latest iPhones and the MacBook Neo are the first real fruits of her leadership, that bodes incredibly well for the future.

New product design at Apple takes a long time. How much of influence those two new figures had on the MacBook Neo?

It’s a good start. Looks quite different than my other web app. Still a lot to implement.

Currently spending Claude AI credits fast and furiously for building this personal bookmarks manager! This time I'm taking a different track, a more more purposely structured approach with the help of Claude advises. I have created and provided a specs.md file referenced by the CLAUDE.md project file located in the root directory of the bookmarks repo. According to my conversation with Claude, it helps reduced the window size. Also, I'm doing all my work on my M4 Mac mini which seems to be much faster than on my aging M2 MacBook Air even though many things runs in the cloud.

Working on my future bookmarks manager webapp. I’m still refining the specs document. I decided to add the possibility to save text quotes in addition to bookmarks. Quotes might be linked to a bookmark. My specs document is quite long and detailed. I wonder how good Claude Code will be to digest all this from the start.

From a public market in Cairo, Egypt.

Neon Signs — Take

Let’s leave the software malaise aside for a moment, hard as that might be; the Neo is a scrappy assemblage of parts, that is trying to find a new route to what Apple considers acceptable, and that is a sign of health.

‘The Window Chrome of Our Discontent’:

This entire idea that application window chrome should disappear is madness. Some people — at Apple, quite obviously — think it looks better, in the abstract, but I can’t see how it makes actually using these apps more productive. Artists don’t want to use invisible tools.

Well, if window chrome is absent, what’s left for Apple to differentiate itself from others than UI elements inside a window? Buttons!

A UI should step back and let user content come forward. But Apple often treats the UI itself as a key part of its identity and differentiation. That creates a tension: the more the UI disappears, the harder it becomes for Apple to stand apart from Microsoft or Google.

I’m really tempted by the MacBook Neo, but really, it makes no sense as an owner of an M4 iPad Pro with a Magic Keyboard: it’s a powerhouse in a compact design. The only problem: iPadOS. It’s THE biggest issue in this story.

Well, it's Friday already! Weather forecasts for this weekend aren't good (rainy, windy). I set out a few goals to achieve this weekend:

1. Start building my AnyBox replacement as a web app using Claude Code. Too bad I wasn't quick enough, the subscription renewal was done two days ago! Let's say now that AnyBox is my backup plan if the web app development doesn't help me achieve the desired state! I'm confident about that one.
2. As Inkwell is heading to its official launch next week, I'd like to record a tour video for Manton's new project. I've been testing Inkwell for the last week, and I find it promising. I'll do the recording on Sunday morning, just in case there are last-minute changes to the web app.

Have a great weekend!

Ok, Apple did a great job this week. A lot has already been said about Apple’s announcements. The MacBook Neo is a killer, even as an entry device. My wife is getting one. It’s the original Mac mini in a laptop shape. Apple did a great balancing act with the Neo. The only two quibbles: only 8 GB of RAM (I wanted 12 GB) and the lack of a MagSafe port.

Now, I hope Apple can do as good a job on the software as it did on the hardware. There is so much to fix.

Glaze, a new app coming from the maker of Raycast. So many questions.

https://www.glazeapp.com

One vendor doesn’t mind high RAM prices: VMware — The Register

The high price of memory and solid-state storage has almost everyone worried – but not VMware, because the most innovative new feature in the Cloud Foundation 9 (VCF 9) private cloud suite it launched last year is memory tiering tech that allows offload of data from RAM to NVMe drives.

VMware has always promoted VCF 9 memory tiering as offering the chance to reduce infrastructure costs by reducing the amount of RAM needed in new servers, and by creating the opportunity to upgrade the NVMe drives in old boxes and effectively increase their memory capacity.

Well, yeah, memory tiering certainly helps reduce the cost of servers, but even NVMe drives, which are built on electronic chips too, are impacted by price increases. And, servers must be compatible with this feature. No magic bullet here.

People’s reactions to Apple hardware announcements so far have been quite positive, if not enthusiastic, much more so than any software announcements in recent years. The difference is stark.

Apple Does Fusion.:

To understand what Apple launched today, we have to go back just over five years, when Apple launched the M1 in November 2020. I wrote then:

“This approach to integration into a single chip, maximum throughput, rapid access to memory, optimal computing performance based on the task, and adaptation to machine learning algorithms is the future — not only for mobile chips, but also for desktop and laptop computers.”

That turned out to be right.

What Apple achieved with their new M5 Pro and M5 Max is quite impressive. Even more impressive is that the architectural decisions made back in 2020 (or earlier) are still paying off today. If only Apple had the wisdom to make similar smart decisions with Siri architecture. Apple seems stuck on redoing its homework forever with software.

iBook > MacBook Neo ? 🧐

Apple Does Value (Week) — On my Om

Apple has decided that $599 is the new floor for a “real” Apple device—not a hand-me-down, not last year’s leftovers, but a current-generation product with current-generation silicon.

If Om Malik is right, this would put the new entry-level MacBook price at 599 US$. The question now becomes: what do you get for that amount of money beyond the A18 Pro chip?

★ HazeOver — Mac Utility for Highlighting the Frontmost Window:

What HazeOver does is highlight the active window by dimming all background windows. That’s it. But it does this simple task with aplomb, and it makes a significant difference in the day-to-day usability of MacOS. Not just MacOS 26 Tahoe — all recent versions of MacOS suffer from a design that makes it difficult to distinguish, instantly, the frontmost (a.k.a. key) window from background windows.1 Making all background windows a little dimmer makes a notable difference.

For some reason, I forgot about this Mac utility. It was installed on my Mac mini, but disabled. It’s now installed and enabled on my MacBook Air with a 40% dimming value. Makes a big difference.

Apple is still proud of Liquid Glass. Found on the iPhone 17e mini website. 😵‍💫

Prices of the new iPad Air and iPhone 17e seems in line with previous generation products they replace and not affected by the current tech environment where prices are going up drastically… it looks rather well too for the upcoming entry-level MacBook pricing.

During any tech transition, the people who retain old-school knowledge while the new-school is developing are particularly valuable. Nobody needs to know punch cards anymore, but I’m sure that while punch cards were being phased out, extensive knowledge about them was incredibly useful.

The same is true about cloud migration. Those who did traditional data centers and started to get interested and involved in cloud migration were (and still are) very in demand.

Of course, I had to create my own… miniroll… nice mini webapp… still wondering if I’m going to support Chris. Probably.

Welcome (back) to Macintosh, by Jesper @ Take

“My hope is that, just as Apple crawled out of a hardware nightmare pockmarked by thermal throttling, keyboards incapacitated by strands of human hair and lack of respect for its users needs, it can choose to refocus its software and its humility too, and stop doing this to the bicycle for the mind.”

I think we will have to wait, the upcoming week’s releases are about Apple hardware…

After relying on ChatGPT as a support tool for most of my AI-related creation activities, recent developments prompted a reassessment of my subscription. With Claude already my preferred tool for coding work and viable alternatives for other features, I made the decision to pause my ChatGPT Plus subscription—but the move revealed deeper issues about data portability and vendor lock-in in the AI industry.

Context and Ethical Concerns

Sam Altman's recent comments about potential military applications of OpenAI's technology sparked a re-evaluation of my relationship with the platform. While AI has tremendous potential for positive applications, the possibility of its use in military contexts raised questions about the ethical implications of supporting such development through my subscription. In contrast, Anthropic—led by Dario Amodei, who advocates for more cautious and ethically-grounded AI development—represents a different approach to building AI systems. By shifting my subscription to Anthropic, I wanted to reward a company taking a more principled stance on AI safety and responsible deployment. It's important to regularly reassess our tools and services based on our values, and to support companies that align with those values.

Finding Viable Alternatives

My shift from ChatGPT to Claude AI actually started well before the recent military controversy. Claude has become increasingly popular in the coding community. When I started new personal coding projects, I naturally gravitated toward Claude because of its growing reputation as the better choice for developers. By the time Sam Altman's comments emerged, I had already been using Claude extensively, which made the decision to pause ChatGPT feel less like a protest and more like a logical continuation of a preference I'd already established. I’m being honest and transparent here.

The image generation aspect of ChatGPT was one of the few features I actively used. Upon investigating alternatives, I found that Midjourney—which I had used in the past—is not only still active but remains the superior choice for creative image generation. For roughly a quarter of what I was paying for ChatGPT Plus, I can maintain full image creation capabilities. Other advanced features available through ChatGPT Plus—like Sora for video generation—were never part of my workflow, which actually made the transition easier. Meanwhile, I've been investing time in Claude Code, Anthropic's code execution feature, which offers capabilities that align better with my development needs.

Data Portability and the Challenges of Migration

Switching AI providers is more complex than simply cancelling a subscription. I had to audit all my existing workflows to ensure nothing would break. This exercise revealed a few dependencies ChatGPT had become in some of my automation systems, but it was a straightforward process to migrate to alternatives once I identified them.

The real challenge lies in data portability. I had previously written about the need for a "takeout" option for ChatGPT (see “A Case for ChatGPT Takeout”), similar to Google's data export feature. One of the most practical issues when leaving a service is extracting your data and conversation history. Discovering that Anthropic provides a custom prompt for importing AI provider memory into Claude was both validating and helpful, though I wish ChatGPT had official support for this kind of migration.

Beyond individual conversation memories, there's a broader systemic issue with how AI providers handle past conversations. Most platforms lock conversations into their own ecosystems with no standardized way to export, archive, or migrate them to another provider. This is particularly problematic for users who may have years of conversations containing valuable insights, code snippets, or creative work. Unlike email or social media platforms, where data portability is increasingly expected, AI providers have been slow to adopt similar standards. The conversations you have with ChatGPT remain ChatGPT's conversations—accessible only through their interface and on their terms. When you leave, you leave that history behind.

A recent article from Techcrunch points to a way to export past conversations, too, by visiting the ChatGPT Settings panel as shown here:

What's Next?

I've used Claude extensively for coding work, but the next few weeks will be interesting as I explore how it handles non-coding prompts and more personal inquiries. There's something intriguing about discovering whether different AI models have distinct "personalities" or approaches to problem-solving. Does Claude respond differently to creative requests compared to ChatGPT? Does it have different strengths when it comes to writing, brainstorming, or exploring abstract ideas? These are questions I'm genuinely curious to investigate. The differences between models might reveal something fundamental about how these systems are trained and what values—intentional or otherwise—are baked into them.

Ultimately, the decision to pause ChatGPT was about aligning my tools with my values. It's a reminder that even as we become dependent on services, maintaining flexibility and periodically evaluating alternatives keeps us in control of our digital lives. The shift also highlights an opportunity to be more deliberate about the AI tools I use and what I learn from comparing them.

Web analytics for my main website, https://numericitizen.me is quite literally in free fall since the beginning of this year. Could this be related to more people using AI for their web browsing needs?

Claude hits #1 on the App Store as users rally behind Anthropic’s government standoff — 9to5Mac

While the long-term consequences of this disagreement are unclear, Anthropic appears to be winning in mindshare, at least for now, in terms of app downloads among iPhone users.

If Anthropic was a publicly traded company ten times their current valuation, would they still stand out against the US government? Asking for a fictional friend at Apple.

Apple Reportedly Expects ‘Major Rush’ of Customers This Week:

The new product likely to receive the most interest is the rumored lower-cost MacBook, which is described as an “incredible value” within Apple, according to the newsletter. Apple believes that a more affordable MacBook will help to “drive a serious number of switchers from Windows machines and Chromebooks,” wrote Gurman.

Somehow, I think that if the price is really competitive, Apple’s bet is that services will subsidize this entry-level MacBook price.

Apple believes low-cost MacBook will be an ‘incredible value,’ tempting switchers: report — 9to5Mac

Internally, the low-end MacBook is being described as an “incredible value,” with Apple believing the launch is going to drive a serious number of switchers from Windows machines and Chromebooks. It could even compel iPhone users without computers to buy their first Mac.

I’m trying to convince my wife to buy one as she finds the iPad to be lacking for certain tasks. I suggested that we buy one of those new entry-level MacBook to try it out without much obligation as we can return the thing in less than 14 days.

Done. I exported my ChatGPT memory to Claude. I’m curious to see how Claude’s answers to my prompts will change from now on. Starting March 12th, I’ll be on Anthropic / Claude AI only.

Currently assessing the impacts of unsubscribing from ChatGPT. Image creation is the most obvious impact, but I rarely use it. I could switch to MidJourney for a third of the monthly price. API consumption is another factor, but none of my four API keys have been used in the last 30 days. According to Claude AI’s examination of my current n8n workflows, three are configured with an OpenAI API key. Investigating further.

Since when is this a thing: Switch to Claude? I mean, I wrote “A Case for ChatGPT Takeout” not long ago!

Moving out of ChatGPT / OpenAI is now a movement, right?

I feel that I'm barely scratching the surface of Claude Code when I see all those videos and articles about it.

Well, well, well... Glass has a new branding. Beyond the blog post explaining the thinking behind this change, I think we lost something in the process. I really liked the G letter; it was more approachable. The new logo looks too "corporate". Still, I love this service very much.

https://glass.photo/brand

There's a quiet trade happening in our lives, one we make constantly without really thinking about it. We sacrifice things we should care about—privacy, ownership, control, independence—in exchange for convenience. The question isn't whether we make this trade, but rather: what conditions make us willing to make it? And nowhere is this more relevant than right now, as we adopt artificial intelligence and other powerful technologies at breathtaking speed.

I call this The Convenience Equation. It's the formula we unconsciously apply to decide whether the friction of doing something the "right way" is worth avoiding, and whether we're willing to accept the risks that come with taking the easier path.

How the Equation Works

The core premise is simple: as perceived convenience increases, our tolerance for risk increases.

When something is incredibly convenient—effortless, seamless, always available—we become willing to overlook consequences we'd normally consider unacceptable. We accept terms we don't read. We hand over data we wouldn't normally share. We lock ourselves into ecosystems we know reduce our freedom. We do all of this because the convenience is genuinely good, and the risks feel abstract. This is the phenomenon that behavioral economists call "inattention"—when convenience is high enough, people often fail to fully evaluate the costs and risks involved.

This Is Not New

The Convenience Equation isn't a modern invention. It's been operating in the background of human decisions for as long as we've had choices to make. The difference is that we've gotten better at hiding the consequences.

Take automobiles. When cars first appeared, they offered something extraordinary: freedom, speed, independence. The ability to go where you wanted, when you wanted. The convenience was revolutionary. But cars also came with a cost we've quietly accepted for over a century: tens of thousands of deaths every year. In the United States alone, more than 40,000 people die in traffic accidents annually. Millions more are injured.

And yet we drive. We accept this equation—extraordinary convenience in exchange for significant risk of injury or death—as a normal part of life. A teenager loses their driver's license and it feels like a tragedy. We complain about traffic, not about the fundamental bargain that cars represent.

That's the pattern. We wanted the convenience, so we accepted the risk. And now we can't imagine life without it, even knowing the cost.

Consider cloud storage. The convenience is undeniable: your photos, documents, and files accessible from any device, anywhere, anytime. Automatic backups. No thinking required. But the tradeoff is significant. A company owns your data. They can access it. They can lock you out with no warning. They can change their terms whenever they want. Your entire digital life can be erased with one flagged account.

Yet most of us accept this. Why? Because the convenience is so high that the risks feel worth it. Research from Stanford economists shows that this inattention to ongoing costs is quantifiable—companies earn 14 to over 200% more revenue from subscriptions when consumers aren't actively monitoring their spending. We keep paying for things we no longer value simply because the friction of cancelling is higher than the friction of doing nothing.

The same pattern appears with streaming services. Instead of owning music or films, we rent access to rotating catalogues. We lose the ability to own anything, but we gain the ability to listen to almost anything instantly. The convenience is real. The loss of ownership is real. Most of us have decided the tradeoff is worth making.

Or consider social media. The convenience of staying connected to everyone, sharing moments instantly, having a permanent record of your life—these are genuinely valuable. The cost is surveillance, algorithmic control of what you see, data harvesting, and effects on your mental health that we're only beginning to understand. Yet the convenience keeps us there.

But nowhere is the Convenience Equation more active right now than with artificial intelligence. We're adopting AI tools at unprecedented speed—ChatGPT, coding assistants, content generators, AI-powered recommendations—because the convenience is extraordinary. Get answers instantly. Write documents in seconds. Solve problems without friction. The benefits are immediate and tangible. Yet we're accepting this trade while genuinely uncertain about the costs. We don't fully know how our data is used. We don't understand the long-term effects on our thinking and decision-making. We can't predict how AI systems will behave in novel situations. The risks around privacy, bias, accuracy, and dependency are largely unknown—or worse, actively hidden. And yet we use these tools anyway, often multiple times a day, because the convenience is too good to pass up. With AI, we're making the largest convenience tradeoff of our lives, except the equation itself is still being written.

The Breaking Point

The equation holds only as long as convenience remains high and risks remain abstract. When the risks become concrete—when you lose access to your account, when a service shuts down, when your data is breached, when terms change in a way that actually affects you—the equation shifts.

Suddenly, you realize you don't own anything. You discover your digital life is rented from a company that owes you no protection. You find out that the convenience came with vulnerabilities you didn't fully understand.

This is the moment many people have: standing in front of their digital life, realizing how much has been handed over, how fragile it all is. But by then, the convenience has usually made untangling yourself nearly impossible. You're locked in—to the platform, the ecosystem, the service. Leaving would require giving up too much convenience to be practical.

When the immediate benefit is clear and the future downside is fuzzy, convenience wins.

The Uncomfortable Truth

The Convenience Equation isn't really about making a calculated decision. It's about how convenience blinds us to the actual cost of our choices. When something is frictionless enough, we don't think about the tradeoff. We just use it.

And that's the genius of it, from a company's perspective. They make their service so convenient that questioning it feels almost ridiculous. Why would you worry about owning your own files when Google Drive is sitting there, syncing everything automatically? Why stress about privacy when everyone you know is on the same social media platform? Why bother keeping local backups when your subscription service takes care of it all?

The answer to all of those questions is the same: because convenience isn't the only thing that matters. But when the convenience is high enough, it becomes easy to forget that it should be. This is why researchers describe the relationship between users and platforms not as a transaction but as a "pay-for-privacy" model—we pay with our data and freedom, and companies profit from the exchange. What makes this sustainable is that the cost remains hidden while the benefit is immediate and visible.

“I have nothing to hide” is really a convenience claim: I’d rather enjoy the benefits now than spend mental energy on hypothetical risks. It’s also a bet—that the context won’t change, that the data won’t be repurposed, and that the platform’s incentives will remain aligned with mine. But privacy isn’t about hiding; it’s about preserving the ability to choose where information about you belongs. Convenience doesn’t just make sharing easier. It makes oversharing effortless.

Finding Your Own Equation Value

The point of naming this isn't to suggest you should reject convenience. It's to make the equation visible.

When you're considering handing something over—your data, your ownership, your independence—it's worth asking: how much convenience am I actually getting? What risks am I accepting? Would I accept these risks if the convenience were lower? Would I still make this choice if I really thought about it, or am I just going along because it's easy?

For some things, the equation might be worth it. For others, it might not be. But at least you'll be making the decision consciously, rather than defaulting to convenience because it's there.

That's the real power of the equation: not to tell you what to do, but to help you see what you're actually trading away.

Generative AI is the perfect convenience drug for mundane tasks: it drafts, summarizes, formats, and fills blank pages instantly. But the risk isn’t that it fails loudly—it’s that it fails quietly. When the output looks polished, we stop reading carefully. The mistake isn’t the model’s error; it’s the human decision to outsource attention.

Three apps recently introduced or updated that don't click with me: Current (RSS reader a la Tapestry), Acme Weather (a pale clone of Dark Sky), and NetNewsWire 7 (a regression from the pre-Liquid Glass era).

Started pondering about using Claude Code to build a custom Micro.blog theme based on my branding and design taste. Seems a good use case of Claude Code. 🤔💭😛

👤 Personal {#traveling,#hobby}

1️⃣ From January 30th to February 12th, I travelled to the Middle East (Egypt and Jordan), which explains why the second edition of this newsletter is a little bit late. In my luggage: my iPad Pro, my iPhone 15 Pro Max and my Nikon Zf with a 40mm lens. I believe the iPad is the best device for travel. All in all, it was a really enjoyable trip, even with some intestinal unease. I shared many photos on my Glass profile if you are curious to get a glimpse. 2️⃣ My experimentation with AI-related tools is taking up a lot of my hobby time. This has negative effects on my other little projects and initiatives, such as producing YouTube videos or maintaining The Craft Bible. I should aim to a more balanced time investment.

🗺️ Discoveries {#gaming}

1️⃣ I'm not a big gamer on computers or smartphones but once in a while I get hooked on a newly discovered game. The most recent one is a tour-style game called “Kingdom Rush Vengeance” available on Apple Arcade. It's a fun game, not too difficult so I can continue play without feeling overwhelmed or discouraged (see screenshot below).

👨🏻‍💻 Writing {#blogging}

1️⃣ My monthly posts digest for January is available, a little late. You can find a summary here on my digests website. 2️⃣ Writing is thinking — the editorial team at Nature. 3️⃣ Outsourcing our writing to LLM might lead to something like passing the same image over and over through an image compression process. Like many things in life, we should strive to find the right balance.

🌄 Photography {#traveling,#photosharing}

1️⃣ During my trip to the Middle East, I had the chance to take more than a thousand photos, many of which are worth processing and sharing. This newsletter header image is one of them. Visit my Glass profile page to appreciate many more of them. 2️⃣ I left Flickr for other platforms, yet its 22-year milestone reminds me that the old photo commons still has a pulse — and perhaps more momentum than I expected.

🍎 Apple & Tech {#design,#liquidglass, #siri}

0️⃣ Apple's history timeline on the Computer History Museum website is nice. 1️⃣ Apple recently released version 26.3 of their OSes. Apple didn’t tweak any of Liquid Glass. The most important tweaks were done with 26.1. Is Apple stubborn and doesn’t want to address user complaints? Or is it that Apple is being… Apple: They prefer to wait longer and have a better fix than patching. This is the approach they used with the dreaded butterfly keyboard in 2018 and 2019. They waited until they had a brand-new set of MacBook models with Apple Silicon to finally fix the keyboard with an entirely new design. I don’t think Apple will completely replace Liquid Glass, but they will eventually fix it. Halide camera app developer, Sebastiaan De With, might come to the rescue. 2️⃣ For iOS 27, Apple is apparently planning a major code cleanup, which could translate into improved stability and battery performance. I'll take that in a heartbeat because, frankly, Apple’s software quality greatly decreased in recent years. Oh, and we could see the new Siri chatbot. 3️⃣ We will have to wait to see a glimpse of Apple's upcoming Siri rework. Poor Apple, that's not an easy one to fix. 4️⃣ While Google, OpenAI et al. are burning a pile of cash on building datacenters, Apple is ... waiting. From a recent article published by Fortune magazine:

“If foundation models are heading toward commodity status, then the strategic value shifts to whoever controls the integration layer and the user relationship. Apple has 2.4 billion active devices. It has the most valuable distribution channel in technology. And its recent moves suggest a deliberate strategy: rather than building frontier models, source them from whoever is best at any given moment.

This is precisely what Apple has done. It partnered with OpenAI in 2024, then switched to Google’s Gemini to power the next generation of Siri. The company is not building the engine; it is curating the best available engine at any given moment, wrapping it in Apple’s privacy architecture, and integrating it across the ecosystem. Own the experience, outsource the commodity.”

📱 Apps & Services {#craft/agents, #appledesign}

1️⃣ I experimented with Craft Agents, a new app built on top of Claude Code. I’m not sure about the value proposition compared to using Claude on the Mac. Both support connections to API and MCP endpoints. For now, I think I prefer Claude AI and Claude Code as two separate tools. That might change in the future, though. 2️⃣ Handmirror was recently updated to version 4 and got many small and big tweaks. Since this update, I've started taking selfies early in the morning or late in the evening. It’s fun. Done over the course of a year, this could be interesting. 3️⃣ Apple is phasing out iWork branding to make room for Apple Creator Studio. It's a controversial move as Apple continues to make inroads in the subscription model for apps that used to be free. It's sad to see, because Apple also continues to push ads in its apps and operating systems to entice users to subscribe. Below is a visual history of Apple's popular apps and their respectve icons. Montage made by BasicAppleGuy.

🚧 Special projects {#webdevelopment,#claude, #vibecoding}

1️⃣ I built a few web apps using Claude Code, and one of them is RSS Flow. It’s an app made just for me, so I don’t plan to share the public URL. It’s a lightweight RSS reader, perfect for when you're on the road or travelling abroad. I’ve been tweaking it for many weeks now, and who knows, it might become my main RSS reader. Without Claude Code, I could never have done it myself in a reasonable amount of time. 2️⃣ Should I call myself a developer if I depend on Claude Code to build small and very focused web applications? I don't think so. Just as we are not calling people “artists” when they take hundreds of pictures with their iPhone. Some might be, but most of them probably aren’t. This reminds me of Matt Birchler's post about those who prefer to code manually (real developers) versus those who like to do some vibe coding (like me). Some people also like to shoot and process their photos manually (like me), but the vast majority use their iPhones.

"The best part of building with AI might be before you write a single line." — Alexander Kucera in Still Possible

📺 YouTube {#ai,#vibecoding,#liquidglass}

1️⃣ Interesting video comparing ChatGPT Codex 5.3 to Claude Code Opsue 4.6 for developing a web application for selling shows. If you are curious to know who wins, watch the video! 2️⃣ Jony Ive's recent project includes designing an EV Ferrari dashboard. From what I'm seeing in this video, I think he did a great job. 3️⃣ Liquid Glass continues to divide the design community. Here's a great video explaining what might be really happening as to why Apple chose to implement Liquid Glass.

🔮 Looking forward {#macbook,#appleevent,#design }

1️⃣ Apple is getting ready for a few announcements in early March. A new entry-level iPhone and an entry-level MacBook are expected, among other things. The latter is intriguing, and I'll pay attention to what Apple has in store. I want a small but mighty device, thin but with stellar battery life, with a minimum of 8GB of RAM, but a built-to-order 12GB option. Connecting an external display should be possible, but it might be too much to ask for such an entry-level MacBook. 2️⃣ The retro-futuristic Ferrari EV car designed by Jony Ive and his firm, LoveFrom. Quite reminiscent of Apple's iconic designs (Apple Watch, Apple CarPlay, iPad). I quite like it, but some people don't. Don't miss the official website of Luce.

"The AI community frenzy around open source agent platform OpenClaw, and its accompanying agent interaction network Moltbook – plus ongoing frustration with AI-generated code submissions to open source projects – underscores the consequences of letting agents loose without behavioral rules." — Thomas Clabum

🌟 Miscellaneous {#musing, #techhistory}

1️⃣ Recently, I came across an article listing ten things the article's author hates. This one, for example, does a superb job and hits many of the things I hate myself. One example: “All modern cars look the same, down to colour options.” (except maybe this Ferrari EV car, as shown in the previous section). In the same vein, I do maintain a /nope page. 2️⃣ Do you remember the Computer Chronicle TV show with Stewart Cheifet? I do. It was a great show to learn about the computer industry back in the day. Mr. Cheifet passed away in December. His obituary is very telling about his popularity and the influence he had on many people's decisions to pursue careers in computer science. 3️⃣ Do you remember the space shuttle Challenger disaster? I certainly do, and I'm not alone. Some still-living engineers from back then do remember, and they wear the weight of feeling powerless because they told the management: no go. The management didn't get the message (or didn't want to get the message).

👉🏻 Main 🌟 Meta 🌟 Blips 🌟 Blog 👀

I wish you a great week! ✌️ 🇺🇦 🇨🇦 🇪🇺 💪🏻

https://notbyai.fyi

ChatGPT’s memory could become a crucial part of the provider–consumer relationship—not just a convenience feature. While we don’t have complete visibility into how OpenAI is building and using its memory system, the practical effect is already clear: ChatGPT can carry context forward, recall user-specific details, and adapt its responses based on what it has learned over time. “Memory,” though, isn’t a single thing; it can include explicit facts you knowingly save, implicit preferences inferred from your behavior, and traces of how you interact. The more we use ChatGPT, the more personalized value accumulates inside the platform, and the more the system effectively “knows” how we think, work, and communicate.

That personalization is impressive—but it also creates a familiar dynamic: switching costs. Today, that accumulated memory isn’t meaningfully portable, even though it arguably should be. Users should be able to leave ChatGPT and take their conversational context with them to another platform—selectively and safely—without having to start from zero. In that sense, a good mental model is Google Takeout: a single place where you can export what you’ve stored with a provider, in standard formats, on your terms. A “ChatGPT Takeout” equivalent for memory could let users download (1) explicit saved memories, (2) preferences and settings, and (3) an optional, clearly labeled package of inferred traits—each separable, auditable, and easy to import elsewhere if the user chooses. And critically, those exports should rely on standard, widely supported data formats (for example JSON, CSV, or plain text/Markdown where appropriate), so portability is real—not a proprietary archive that’s technically “exported” but practically unusable.

Of course, portability can’t be naive—exporting “memory” raises real privacy and security risks, especially if it includes sensitive details you forgot you shared or traits inferred about you. That’s exactly why portability should be designed with strong safeguards: inspectable records, granular consent (what to export and what not to), clear provenance (saved vs inferred), and revocation. If memory is going to become part of the relationship, users should have meaningful control over it—including the ability to take it with them.

Last week I read about custom vibe-coded RSS readers: quick and scrappy tools, non-polished, built to solve a particular need of their owner. Today I read about Current, which has thoughtful design, interesting concepts, and attention to detail.

I wonder if he is referring to one of my recent posts about RSS Flow... 👀

https://jeroensangers.com/2026/02/18/the-artisan-and-the-tinkerer.html

In case you didn't know already, this blog post is hosted on the cool blog hosting service with a cool name called "Scribbles.page". If you want to start blogging, follow this invite link because it's the only way for now to join Scribbles.page.

I've committed to presenting to my colleagues on the potential impacts of the latest IA-related developments on their day-to-day work. I won't go down the "AI will replace your job" route; instead, I'll focus on "AI will augment you". I'm using ChatGPT to build the framework for my presentation, and boy, it's so much fun compared to starting from a blank page.

I'm back from my two-week vacation in Egypt and Jordan. It was great. Jet lag is in full effect. Check my blog for the usual random travel notes.

Somewhere in Jordan desert.

Tomorrow, I’m starting a two-week vacation in the Middle East, so…

1. I'm patiently selecting videos to download on my iPad for some in-flight entertainment. The last time I did that proved to be a waste of time: all my Apple TV videos refused to play because of an unknown error. I was like 😡 . This time, I'm going to test my videos in air plane mode before leaving the house.
2. I'm winding down my work on most of my projects, mostly involving webapp development with Claude Code. I'm done with my photo-sharing website for my family and closed friends. It's super cool 😎 and it is ready for use during my vacation. Of course, I still plan to share my best photos on Glass.
3. This break is a welcomed one. I've been spending a lot of my spare time on AI stuff. I feel a little bit tired. Taking a break from most of my screens will be salutary. I know that I'll come back fully loaded with ideas and energy.
4. Expect lower-than-normal activity on my blog in the next 15 days. That's expected. Thanks to my automated timeline summaries, I'll keep an eyes on what is going on.

Cheers.

Tim is facing criticism for his repeated attendance at Trump's events. I'm unsure if [he feels trapped](https://om.co/2026/01/27/a-ceo-captured/). If he strongly disagrees with the current US administration but prioritizes Apple's shareholders' value in his decisions, that is his choice. He could also choose to resign as Apple's CEO, citing a conflict with his values. Yet, he remains in his position.

Ok, this is something interesting. Probably gamechanging, too. I'll set it up on my M4 Mac mini which I don't use much since I switched jobs in mid-2025. Now, I think I have found a new use case for it.

[https://clawd.bot/](https://clawd.bot/)

👤 Personal {#blogging}

1️⃣ I've been quite busy during the Holidays with my digital hobby. This year started with a bang! I'm ecstatic, actually. It's been less than a couple of weeks, and the amount of "work" accomplished is simply astonishing. I couldn't have done it without my determination, with a bunch of wild ideas and ... Claude AI. I'll take a two-week vacation in early February, which will help me consolidate my learning and experience. 2️⃣ I started a new website (digests.numericcitizen.me) and talked about it here. I'm excited about that one because of the way it is built and because I have more plans for it, too. 3️⃣ For creators like me, people can be weird. Thankfully, I rarely get these type of comments on anything that I create and share. This was a parody blog post from Matt Birchler. I'm guessing he gets those bad comments way too often, leaving him without a word.

🗺️ Discoveries {#accessories}

1️⃣ Clicks introduced the Click Power Keyboard, a MagSafe battery pack and a physical keyboard all-in-one device for the iPhone. I'm not sure I'm the target customer for this, but I applaud the company’s imaginative but off-track accessory. I was a fan of Blackberries back in the day, and I do see some use and edge cases where a physical keyboard would be helpful. But those edge cases are... edgy, and I don't think they warrant a new device in my pocket. 2️⃣ There is a new Apple Store in downtown Montreal. The store was previously about 100m west of today's new location, on same street. I paid a visit and took some photos, see next section.

🌄 Photography {#traveling, #applestore}

1️⃣ I had the chance to visit the relocated Apple Store on Ste-Catherine Street, downtown Montreal and shared my observations as well as my best images of the place. I couldn't take my Nikon camera with me because the battery was depleted, and I couldn't wait to recharge it. I managed to take a few good pictures with my phone, though. 2️⃣ My next photographic experience is getting closer, when I visit Egypt at the end of January, early February. Until then, I'm utterly quiet on that front.

🍎 Apple & Tech {#ai,#design, #macostahoe, #appstore}

1️⃣ Apple's macOS Tahoe might be the most poorly received release in terms of design. Some believe Liquid Glass isn't suitable for a desktop operating system. I agree: the glass metaphor works well for a device like the iPhone, which is essentially a slab of glass, but a desktop computer isn't the same. Critics also criticize the inappropriate use of icons in menus, which is the latest point of contention. Although many seem to share this concern, I personally like seeing icons in menu items. You should decide for yourself. This detailed blog post presents a strong argument against their use. I shared a more detailed take on this. 2️⃣ Like if it was possible, X / Grok are in the news again for allowing people create and post all sorts of very questionable content on the network. Many people are asking for Apple and Google to remove those apps from their respective App Stores. Despite what appears to be a patent violation of their store's rules, they still don't budge. Why? Probably a good idea to look at mounting fear of ... Trump. Gruber’s words are worth a read. 3️⃣ I rated each Apple product from 1 to 9. Here are the results.

“Claude Code has the potential to transform all of tech. I also think we’re going to see a real split in the tech industry (and everywhere code is written) between people who are outcome-driven and are excited to get to the part where they can test their work with users faster, and people who are process-driven and get their meaning from the engineering itself and are upset about having that taken away.” — Ben Werdmuller

📱 Apps & Services {#dataprotection, #bookmarking,#ios26}

1️⃣ Are you one of those who think that data in the cloud is a backup, or even being backed up? Well, think again. The cloud is not a backup solution if this is the primary storage of your data. That's the case with iCloud Photo Library or iCloud Drive. Because your data is on the device and in the cloud doesn’t mean they are backups of each other. There is a small Mac utility you can buy that enables real backups, called Parachute Backup. It's cheap and apparently effective at backing up your data to a destination of your choice. Disclaimer: I don't use such a solution. But I should. 2️⃣ If you happen to save a lot of bookmarks for later reference, consider reading The Newsprint review of MyMind. It's a good overview of what makes MyMind so lovable. I tried it myself and like its design, but I prefer AnyBox, which is a better fit for my needs. 3️⃣ Early reports indicate that iOS 26 adoption is low at around 18%, but data from a specific app suggests that about 70% of its active users have already upgraded, highlighting a potential discrepancy in the overall adoption figures. Maybe power users are upgrading, but normal people with lighter usage aren’t?

🚧 Special projects {#automation,#vibecoding}

1️⃣ A lot happened since the previous edition of this newsletter. I was essentially focused on building automation workflows in n8n, most of my hobby time. You can read all about it right here. Besides that, I also worked on building small, focused web apps with Next.js and hosting them on Vercel using Claude Code. It's a fascinating process: writing down prompts that describe the final product and watching Claude code, spitting out code and strategies to build a successful app, doing what I described in the first place, no programming required on my part. I call this my modern Lego set.

📺 YouTube {#tech, #design, #ai}

1️⃣ When Apple brags about putting billions of transistors on a chip like the M5, what doesn't it represent in reality? How big or small does this fact represent? Well, Marqus Brownly made a video to show how small things are these days. It's really well done. 2️⃣ The flat edge dilemma: A good video about explaining major design constraints and how they affect product shapes and sizes. 3️⃣ Paris timelapse from -300 to 2025. Quite impressive. 3️⃣ We are hearing a lot about sycophancy when we refer to LLM. What is this? Sycophancy is the tendency to excessively flatter or agree with someone in order to gain favor or approval. More details and explanation in this video.

🔮 Looking forward {#digg, #openai, #chatgpt}

1️⃣ Digg is officially in public beta, after a rather long private beta period, which I took part in. People want Digg to become a new Reddit, but I'm not sure this is what I want. I'm not sure where it's going, I'm not even sure we need another social network. From what I'm seeing, many Digg posts are already available elsewhere and have very limited user engagement. Just to kick the tires, I wanted to create a user community about Apple, but someone beat me to it, and the name was no longer available. Instead, I created Apple Design, which can be found here. There are twelve members at the time of this writing. You can find my Digg profile here. 2️⃣ Well put, Matt, well put: ChatGPT enshittification has officially begun. Now, for 8 US$ a month, you get ads within your chat sessions. I expect ads to come to other pricing tiers, too, eventually. When we see ads, we become the product. Sad.

🌟 Miscellaneous {#space,#software}

1️⃣ SpaceX gets the green light to launch 7500 more Starlink satellites in space, contributing not only to increasing coverage and bandwidth but also to the Kessler Syndrome. The Kessler Syndrome, also called the orbital debris cascade, is a theoretical scenario in orbital mechanics describing a self-sustaining chain reaction of collisions among space debris. Proposed by Donald J. Kessler in 1978, it predicts that as the density of objects in low Earth orbit (LEO) increases, collisions could generate debris that, in turn, causes further impacts, making certain orbital regions unusable for satellites or spacecraft. 2️⃣ Now that we are destroying space, are we also destroying software? Antirez says yes. 3️⃣ Also from the same author, building software is hard, especially open-source software. Hard enough to move on. 4️⃣ Have you heard about the enchittification phenomenon? This article from Mitch Wagner explains how dominant tech platforms follow a predictable trajectory: they begin by serving users well, then progressively degrade the experience as monopoly power takes hold. This process—called “enshittification”—extends beyond bad products to include labor exploitation and broader economic harm. The author argues that reversing this trend requires meaningful antitrust enforcement and renewed competition, not better design or goodwill. OpenAI might be on the trajectory of enchittification with ChatGPT Go. 5️⃣ Is software dead? It might. Thanks to AI. Again.

👉🏻 Main 🌟 Meta 🌟 Blips 🌟 Blog 👀

I wish you a great week! ✌️ 🇺🇦 🇨🇦 🇪🇺 💪🏻

https://notbyai.fyi

On a snowy, rather grey day, lacking luminosity, I paid a visit to the new Apple Store on Ste-Catherine Street in downtown Montreal. Here are a few observations.

It feels so different, much warmer, more welcoming. I took a few images with my aging iPhone 15 Pro Max so you could get a sense of the interior and exterior design.

I think Apple's commissioned architects did a great job restoring the building. There's a strong sense of humility and honesty in the material choices. The wooden ceiling helps keep the sound level acceptable, toned down a bit. Apparently, Apple chose local materials.

The windows are tall, with a small portion at the top embossed with a pattern that adds a nice mid-century touch to the look. The lighting is just right, nothing too intense, helping keep the calmness of the design.

We didn't get a tree or other vegetation touches, sadly. It would have made the place feel even more "organic". This is not, to my knowledge, an Apple flagship store. Maybe the designers felt the place didn't have enough space. Also strange, since this is a three-story building, I was expecting a second level, but apparently, there was nothing accessible to the public. Hence, we lost the iconic and frosty stairs from the old store. Again, maybe to keep as much space as possible for the customers and the products. You can get a quick video of the store, right here, on my blog.

The place looks less busy, too, from a product display perspective. Accessories are well organized on a few stations along the store's exterior walls, while devices are on the classic wood tables, symmetrically placed in the store's main area.

It's the end of an era, that's for sure. Or the beginning of a new one. The old store is about to disappear from view in the city. The store was smaller, colder and a glimpse of Apple Store ideal, more than fifteen years ago. This is where I bought my first iPhone. And my first iPad. And my first Apple Watch. That store reminds me of Steve Jobs' era. The new one is more about Tim Cook's era. What comes next is up to anyone to guess.

By popular request, here’s the documentation for my n8n workflow. This documentation was created with Claude AI using Claude Skills and was slightly tweaked to remove any sensitive data. The diagram was manually added.

Over the past few weeks, I’ve been on an intensive learning journey exploring automation, cloud deployment, and AI integration. I’ve been hands-on, building real workflows and connecting actual services. Here’s what I discovered along the way.

Getting Started with Automation

The foundation of this exploration was deploying n8n as a self-hosted instance on a cloud provider. This wasn’t just about clicking a button—it required understanding infrastructure, configuration, and the basics of running a service in the cloud. Once that was in place, I could start building workflows.

Building basic workflows in n8n taught me what it actually means to create a functional automation. It’s not enough to have a good idea; you need to understand how data flows through your workflow, how triggers initiate actions, how conditions branch logic, and how errors are handled. Meeting all the requirements for a working workflow meant learning to think systematically about each step and its dependencies.

Accelerating Learning with AI

One of the biggest breakthroughs was leveraging Claude AI to accelerate my learning across different subject matters. Rather than struggling through documentation alone or spending hours debugging, I could ask targeted questions and get explanations tailored to my specific use cases. This fundamentally changed how quickly I could iterate and experiment.

Claude became my learning partner—helping me understand concepts, troubleshoot issues, and even write code. This wasn’t just about saving time; it was about compressing what might have taken weeks of traditional learning into days of focused experimentation.

Building and Connecting

From there, I expanded into multiple directions simultaneously. I deployed Next.js apps on Vercel using Claude Code, which gave me a way to build custom web interfaces quickly. I integrated GitHub for continuous delivery, automating the process of pushing code changes to live services like Scribbles and Micro.blog.

But the real power came from connecting external services directly into n8n workflows. I learned to interact with Telegram, Discord, Micro.blog, and Tinylytics through their APIs, webhooks, and HTTP requests. Each integration taught me something different about how modern services communicate with each other. Some services have well-documented APIs; others require reverse-engineering their webhook payloads. Some are straightforward; others have quirks you only discover through experimentation.

The Deeper Challenges

The more complex problems emerged when I tackled data persistence and LLM integration within n8n. Adding state management to automation workflows isn’t trivial—you need to decide where to store data, how to retrieve it, and how to keep it synchronized across multiple workflow runs. It’s one thing to run a workflow once; it’s another to run it reliably over time while maintaining context and history.

Incorporating AI services—whether through pay-per-use models like Claude or subscription-based services—required careful consideration. I had to think about cost implications, rate limits, and how to structure requests efficiently. Suddenly, every API call had a price tag, and I became much more conscious of resource consumption.

Key Insights

What stands out most is a clearer understanding of tool selection. Each platform has its place, and knowing when to use n8n versus a custom Next.js app versus a direct API call makes all the difference. Sometimes the right answer is a simple webhook; sometimes you need the flexibility of a full application. This contextual thinking has become invaluable.

I’ve also learned to transpose ideas into concrete use cases, leveraging service APIs from Scribbles, Tinylytics, and Micro.blog in ways I hadn’t considered before. What started as “I wonder if I can connect these services” became “Here’s a specific workflow that solves a real problem.”

I’ve discovered how to make the most of services I was already depending on—Micro.blog and Inoreader—by understanding their capabilities more deeply. These tools had features and integrations I’d overlooked, and now I’m using them in ways that actually enhance my workflow.

I’ve also expanded my toolkit with utilities like VS Code, GitHub, and Postman, each playing a crucial role in different parts of the workflow. VS Code became my development environment, GitHub my version control and deployment trigger, and Postman my tool for testing and understanding APIs before integrating them into n8n.

The Bigger Picture

The journey has been about understanding not just individual tools, but how they fit together in a larger ecosystem. It’s about recognizing that modern development isn’t about mastering one tool—it’s about understanding how to orchestrate multiple tools to solve real problems. And it’s about using AI not as a replacement for learning, but as an accelerant that lets you learn faster and go deeper.

For months, I’ve been publishing my weekly newsletter, The Ephemeral Scrapbook, using a manual process: write in Craft, export to Ulysses, copy to Ghost, reformat everything, add images, fix formatting issues, and finally publish. It worked, but it was tedious and time-consuming.

Today, that process is fully automated. Here’s how Claude and I built it together.

The Challenge

My workflow had become a bottleneck:

• Writing newsletters in Craft Docs (my preferred writing environment)
• Exporting to Ulysses as an intermediary step
• Manual copy/paste to Ghost (my publishing platform)
• Reformatting all the markdown and HTML
• Dealing with Craft-specific formatting that Ghost didn’t understand
• Adding metadata like excerpts and tags manually

I wanted automation, but I also wanted to understand the infrastructure I was building. That’s where working with Claude became invaluable—not just executing commands, but learning and iterating together.

The Solution: n8n Workflow Automation

We decided to build an n8n workflow that would:

1. Search for a document in Craft by title
2. Fetch all the content blocks
3. Transform Craft’s markdown/blocks into clean HTML
4. Publish to Ghost as a draft
5. Return confirmation with the post URL

Simple in concept, complex in execution.

The Journey: Key Milestones

Milestone 1: Understanding the Architecture

Challenge: Should we use multiple workflows or one unified workflow?

Decision: One end-to-end workflow that handles everything from search to publish.

Learning: Simplicity wins. Rather than orchestrating multiple workflows, we built one cohesive pipeline that’s easier to debug and maintain.

Workflow nodes:

• Webhook (trigger)
• HTTP Request (search Craft)
• HTTP Request (fetch document)
• Code (transform to HTML)
• HTTP Request (publish to Ghost)
• Respond to Webhook

The Iterative Building Process

One of the most important decisions we made was to build and test incrementally. Rather than assembling the entire workflow at once and hoping it would work, we added one node at a time, testing after each addition.

The Testing Cadence:

1. Add Webhook → Test: Confirmed the webhook received the query parameter correctly
2. Add Search Node → Test: Verified we could find the document and get the correct document ID
3. Add Fetch Node → Test: Checked that we retrieved all 54 blocks of content with the proper nested structure
4. Add Code Node → Test: Validated the HTML transformation, checking for clean output without Craft tags
5. Add Ghost Publish Node → Test: Ensured the post was created as a draft with all content intact
6. Add Response Node → Test: Confirmed the workflow returned post details back to Claude

Why This Mattered:

Each test revealed issues that would have been much harder to debug in a complete workflow:

• The search node helped us understand Craft returns multiple matches (we needed the first result)
• The fetch node showed us the nested structure (parent document → edition page → content blocks)
• The code node iterations caught formatting issues (<callout> tags, ## symbols, <highlight> tags)
• The Ghost publish node revealed we needed the ?source=html query parameter

By testing at each step, we could pinpoint exactly where problems occurred. When something didn’t work, we knew it was the node we just added, not some mysterious interaction between distant parts of the workflow.

This incremental approach turned what could have been hours of debugging into a smooth building process. Each successful test gave us confidence to move forward, and each failure was easy to isolate and fix.

Milestone 2: Building the HTML Transformer

Challenge: Craft uses its own markdown dialect with special tags like <callout>, <highlight color="blue">, and markdown headers in text blocks.

What we built: A comprehensive JavaScript transformation engine that:

• Removes Craft-specific tags (<callout>, <highlight>)
• Converts markdown formatting (bold, italic, links, code)
• Processes different block types (text, headers, quotes, code, images, videos)
• Handles rich URL blocks (YouTube embeds)
• Preserves anchor links for internal navigation
• Generates proper HTML for Ghost’s Lexical editor

Key functions:

• markdownToHtml() - Converts inline markdown to HTML
• processBlock() - Handles each block type (text, image, richUrl, code, line, etc.)

Milestone 3: Testing and Validation

The Process:

• Test with real content (Edition 2025-52 with 54 blocks)
• Verify HTML output in Ghost’s editor
• Check for Craft formatting artifacts
• Confirm all sections, videos, quotes, and images are preserved

Quality Checks:

• ✅ No <callout> tags
• ✅ No <highlight> tags
• ✅ No ## symbols in headers
• ✅ All YouTube videos embedded correctly
• ✅ Blockquotes formatted properly
• ✅ Images included
• ✅ 9-minute reading time (17,000+ characters)

The Final Workflow

Input: {"query": "The Ephemeral Scrapbook — Edition 2025-52"}

Output: Draft post in Ghost with:

• Complete HTML content
• All formatting preserved
• Clean structure
• Ready for manual review (add images, tags, excerpt)

Execution time: ~3-4 seconds total

• Search: 1-2 seconds
• Fetch: 1-2 seconds
• Transform: 36-84ms
• Publish: 600-900ms

The Tools

• Craft: My writing environment with a powerful API
• Ghost: My publishing platform with a robust Admin API
• n8n: Workflow automation platform (self-hosted on DigitalOcean)
• Claude AI: My pair-programming partner via MCP (Model Context Protocol)

The Result

The workflow is production-ready. My publishing workflow went from 20+ minutes of manual work through Craft, Ulysses, and Ghost to a single command:

“Claude, publish Edition 2026-01 to Ghost”

And it just works. 🎉

The conversation around AI has become exhaustingly polarized—breathless evangelists on one side, dismissive skeptics on the other. I find myself somewhere in the middle: curious but cautious, experimental but principled.

As I look ahead to 2026, I want to articulate how I envision AI's role in my work as a technology blogger, content creator, and independent web advocate. This is informed by the guiding principles I documented (https://meta.numericcitizen.me/ai/) and shaped by my experience as a hobbyist who loves exploring new information technologies for creative and learning aspirations—not career goals.

AI as Learning Accelerator

I see AI as a force multiplier for learning, particularly for understanding specific technologies where traditional resources are scattered.

As someone who explores various platforms and tools—both for my own use and to cover on my websites and YouTube channel—I'm constantly encountering technologies with varying learning curves. When I'm building small web applications, experimenting with APIs or MCP, or creating automation workflows, documentation can be scattered, incomplete, or written for different skill levels than where I'm starting.

This is where AI becomes invaluable by explaining specific technologies in ways that match my current understanding and specific needs. When I'm trying to understand how to connect two services or figure out why something isn't working, AI can tailor explanations to my specific question and context.

I'm using AI to understand, not to blindly generate solutions. This is about making the process of understanding specific technologies more efficient, so I can spend more time on the creative and analytical work that actually matters. Here are two examples.

Claude Code helps me understand how to approach problems. When I build small projects that support my creative work, it helps me see how experienced developers think about solutions. My goal is to understand enough to build the specific tools I need and satisfy my curiosity about how systems function.

n8n is about making specific parts of my creative workflow more efficient and predictable where it genuinely makes sense. AI supports this by helping me understand how to configure workflows and debug issues—freeing me to focus on content creation, learning, and exploration. As I mentioned in my year-in-review, n8n is becoming my digital playground for 2026.

Summarization: The Essential Use Case

The use case I think about most is summarization. As a technology blogger, I follow numerous information sources across the indie web, productivity software, and information technology. I consume more content across many sources than I can possibly read or watch in full depth.

AI-generated summaries help me triage effectively. I can quickly determine whether content deserves my full attention or whether the core insights are adequately captured. This isn't about replacing primary sources—when something matters, I still engage with the original. It's about making the discovery process manageable and expanding my capacity to cover more ground in content consumption.

My pragmatic conclusion for 2026: I prefer an imperfect summary to missing out on important content entirely.

Connecting the Dots: AI as Writing Partner

One aspect of AI that I find genuinely valuable—and that wasn't even possible five years ago—is using it as a writing assistant. This is another way AI helps me connect the dots.

When I'm drafting essays, blog posts, or thinking through complex topics, AI helps me make connections between concepts and ideas that I might not see immediately. I might be writing about automation workflows and AI can help me recognize how that relates to something I wrote about platform independence months ago. Or I'm exploring a new productivity tool and AI helps me articulate how its approach differs from patterns I've discussed before.

AI helps me see the larger patterns in my own thinking, suggesting connections that I then evaluate and develop in my own words. It acts as a thinking partner that helps me connect dots across my work in ways that make my writing richer and more coherent.

This capability has changed how I approach longer pieces. I can work through ideas conversationally, test connections, and refine my thinking before committing words to the page. Five years ago, this kind of interaction simply didn't exist. Now it's become a valuable part of how I develop my ideas and structure my writing.

Staying Curious, Vigilant, and Critical

As AI capabilities continue to evolve, I'm genuinely curious about how these offerings might impact my digital life as a creator. Will new AI tools emerge that fundamentally change how I research, create, or publish content? Will AI integration become so seamless in the platforms I use that it shifts what's possible in my workflows?

I don't know the answers, and that's what makes 2026 interesting. I want to stay open to possibilities while maintaining the critical lens that has guided my approach so far.

This means continuing to evaluate AI offerings against my established principles: Does this solve a real problem or create busywork? Does it align with my values around privacy and independence? Does it amplify my voice or dilute it? Does it support the indie web ecosystem I advocate for?

The AI landscape moves quickly, and not every development deserves equal attention or adoption. My commitment for 2026 is to remain curious about what's emerging, vigilant about how these tools actually perform in practice, and critical about their true value proposition.

The Independence Paradox

There's an obvious tension here: I advocate for indie web values and platform independence, yet I rely on Claude and ChatGPT—centralized AI services from large tech companies.

I think about this tension as the difference between tools and platforms. I'm using AI as production infrastructure to support work I publish on systems I control, not building my digital presence on AI platforms themselves. It's more like using VS Code than like building my blog on Substack.

But the tension is real. These services could change pricing or terms. They involve sending data through commercial systems. They create dependencies.

For now, I'm comfortable with this trade-off because AI helps me build and maintain my own infrastructure more effectively. But I'm watching it. If the dependencies start compromising the independence I value, I'll need to reconsider.

I suspect many in the indie web community face similar tensions as they evaluate AI tools.

Looking Ahead

I haven't landed on either extreme—the evangelists proclaiming AI will revolutionize everything or the skeptics dismissing it as worthless hype. I'm a hobbyist learner and creator with established principles and a commitment to documenting what works—and what doesn't.

For me in 2026, AI means:

• A learning accelerator for understanding specific technologies
• A processing tool for managing information consumption through summarization
• A writing partner that helps me connect concepts and ideas across my work
• An explanation tool that adapts to my context and learning needs
• A support tool for selective automation that makes creative work more efficient

But always with me in the decision-making seat. My curiosity drives what I explore. My judgment determines what I publish. My values guide how I use these tools. And my creative aspirations, not career goals, shape how I engage with technology.

The indie web has always been about taking ownership of your digital presence, choosing tools intentionally, and building for yourself. AI, used thoughtfully, can be part of that story in 2026—not as a replacement for human creativity and judgment, but as another tool in the independent creator's kit.

Here’s a quick demonstration of the Microblog Poster web app I mentioned in my previous blog post.

As recently shared on my blog, I have finished (or mostly finished¹) building a simple front end for Micro.blog. This front end, as depicted in the following screenshot, presents the user with a straightforward UI: a title field, a body field, blog post categories, and a Publish button—very focused, with no distractions. It works on desktops and mobile devices. I even added PWA support. But why did I build this?

First, I wanted to dip my toes into Vercel. I’ve recently stumbled upon many posts about web apps built and deployed on Vercel by people claiming no programming experience. Most people were using Claude AI or Claude Code to describe their app and deploy it to Vercel. Some apps were impressively designed and functional. Yet, I thought it wasn’t that easy and required a lot of technical knowledge. I was intrigued. I was “mostly” wrong.

I’ve been using Claude AI since mid-December, in conversational mode, for different tasks, including getting explanations on building apps on Vercel and other platforms. I’ve been looking for small project ideas since then. Building a simple front-end to Micro.blog quickly became the perfect test. Micro.blog offers a simple API for many things. Using Claude and the API documentation, I asked Claude AI whether it was possible to build a simple UI for posting on Micro.blog. Sure enough, it was. My initial prompt describing the envisioned app follows:

Let’s build a web app hosted on Vercel that lets me to write blog posts for Micro.blog. The form will include only two text fields: a blog post title and the blog post text itself. Include a character count that will update as I type. Maximum of 5000 characters. The web page should include a title “Microblog Poster", centered.

Micro.blog supports Markdown, so the blog post text field should support it too.

The authorization token should be stored in an environment variable named “microblog_token” which I will provide once the project is created on Vercel.

I will use a GitHub repo, which should be named after the application name: “(redacted)” where the app will use the full URL: https://(redacted)

Provided that Micro.blog supports draft posts as exposed in the Micro.blog APIs, a toggle named “Draft” should be on the web form and be off by default. When enabled, this means I can send the blog post to Micro.blog but with a draft status. Otherwise, the blog post is published.

The initial state of the web app is to list all available blog post categories as a series of checkboxes, all off by default. You will need to retrieve possible blog post categories during the initialization phase. A blog post can have more than one category selected or none. This list of checkboxes should be left-aligned. The category list should be saved in the browser’s local storage and initialized on the first invocation of the web app.

The form will contain a button “Publish” centered horizontally (like all the other UI elements, except the toggle underneath the Publish button which should be left aligned. Once clicked, if the post operation is successful, add a small banner (centered) telling me the operation was successful with an appropriate message.

For a non-draft post, after hitting Publish, the form should display a clickable link to the blog post’s final URL. For the draft post, you should display the clickable link to the draft post instead.

Images or any other attachments are not needed.

You can look at micro.blog API documentation in the following URLs:

For reading data from Micro.blog service: https://help.micro.blog/t/json-api/97

For posting to Micro.blog service: https://help.micro.blog/2017/api-posting/

After a few hiccups and errors, it eventually worked. I had to install GitHub Desktop on My Mac as well as Visual Source Code, but I eventually realized Claude AI wasn’t optimal. I ultimately switched to Claude Code to iterate on the initial release. My experience was so much smoother. I do experience so weird issues with GitHub, but it seems without impacts on the deployment.

So, building the app requires a GitHub repository for holding the source code. Vercel connects to my GitHub repo, and as soon as a new commit is made, a new app deployment happens; It’s all automatic. One important thing to know: a project environment variable² to hold the Micro.blog app token is needed before trying the app for the first time.

My first try mainly worked as expected. I made sure to have a draft mode available in the UI so that I don’t mess up my timeline with test posts. Once the app is deployed and available for use, any modifications are made through prompting Claude Code on my local machine. Code changes are pushed to GitHub on demand. It takes a few minutes for a new iteration to be available for testing.

If you have any questions or comments, feel free to post them, and I’ll do my best to answer them to the best of my knowledge.

One more thing: Vercel is free to use in my case because my app is relatively lightweight. Lastly, one benefit of building my app is that it will circumvent a design issue with Micro.blog’s post editor on the web: the title field and categories aren’t listed by default. I find this to be annoying. My app shows them. I’m happy with that.

👤 Personal {#recognition}

1️⃣ If you’ve been following me for a while, you probably know that I'm a big fan and power user of Craft. They recently ran a challenge in their Slack community to have people build different workflows that leverage Craft APIs or MCP functionality. I’ve submitted my workflow called “The Year in Review Writing Assistant“ and won a 500 $US prize! That wasn't expected, really. Yet, I'm glad that the Craft team recognized my work.

🗺️ Discoveries {#internet #yearinreview #retro #tech}

1️⃣ Here's a massive recap from Cloudflare Radar for 2025. There are so many stats and graphs in this visual summary. From emails, device usages, protocols, security, and so much more, many different things are covered in this review. 2️⃣ If you are a fan of retro-computing and the heyday of the personal computer era, don't miss Stone Tools website. VisiCalc, HyperCard, Superbase, or Aldus PageMaker, do you remember these? I do remember mostly Hypercard and PageMaker because I was a big fan of them. This website is focused on work-related computer software. It's so fun to go back in time when reading intricate details about a computer program and its surrounding context at launch and in use.

"Standards that enable direct publisher–reader relationships are inconvenient for companies whose business depends on sitting in the middle." — Ben Werdmuller

👨🏻‍💻 Writing {#rss}

1️⃣ If you are a writer, a blogger or any content creator on the web, please, do yourself and your audience a favor, enable RSS feeds on your little corner of the internet. 2️⃣ Speaking of RSS feeds, it seems there isn't enough RSS feed feaders already and the founder of Ghost, a well-known publishing platform on which this newsletter is running, is building a new one named Alcove. I don’t want to set my expectations too high, even if I like what this guy is doing in general. How many new RSS readers came to the light while pretending to be the new way of consuming content? Reeder Next is one of them. It's nicely designed, but it's very limited, and my gut feeling is that it's not doing really well. 3️⃣ There is a little controversy about the Alcove announcement. People, including me, were surprised to see its author, a proponent of open source and open web, use the infamous X network to post a teaser. When it comes to discoverability, principles seem easy to forget, I guess. 4️⃣ Why am I talking about RSS in this writing section? Because RSS is the conduit for sharing your writings with the world without any engagement tricks.

"Most people have never lived outside the mind’s theater. They experience life almost entirely as commentary…as stories about what’s happening, what might happen, what should be happening, and who’s to blame that it isn’t. Inside that theater, constant agitation feels like virtue. Outrage feels like responsibility. Anxiety feels like engagement. And calm is interpreted as indifference. "— Damien Echols, Fighting Shadows

🌄 Photography {#ipad #art}

1️⃣ If you got a new iPad for Christmas to replace an older one, you might want to consider transforming the old one into a photo frame using this app. You will need to use Apple's iCloud Photo Library, though. It's a good way to extend the life of your electronics. 2️⃣ Showing dedication to Mount Fuji in photography—really spectacular images of this legendary mountain. 3️⃣ A concise reflection on building a daily photography habit by abandoning self-imposed labels, noticing beauty everywhere, and treating every photograph as practice rather than a special occasion. I should take note. 🤦🏻‍♂️ 4️⃣ I'm a fan of old illustrations, especially in the early 1830s. 🤩

🍎 Apple & Tech {#digitalservices #ads}

1️⃣ This story is about having an Apple Account (previously known as an Apple ID) locked down because of a failed attempt to redeem an Apple Gift Card. This can be devastating because a locked-down account means no more access to Apple services, Apple devices and Apple purchases or subscriptions. Thankfully, the story ends well, thanks to intense media buzz. Apple doesn't like bad press. The last time I tried redeeming an Apple Gift Card, it went well (I had five of them). But now, I'll think again. If my Apple Account ever gets locked down, I don't have the required influence to get the attention from the Apple executive team. Read some people’s reactions as documented by Michael Tsai. Scary. 2️⃣ Speaking of Apple executives, why this turnover of executives and high-ranking personnel when the iPhone seems invincible and keeps breaking sales records? 3️⃣ More ads are coming to the Apple App Store. Yep. More ads when you search for something. With all the junk already filling this digital space, making it hard to find something, it looks less and less Apple-like, more like today's Google. 4️⃣ While more ads are coming to Apple's platforms, Maps loses Flyovers! It was cool when it was introduced in iOS 8 but keeping them updated might cost Apple a price they no longer want to pay.

“There’s a lot of hate for Alan Dye right now, but keep in mind that the dude did not magically promote himself to a leadership position, at either Apple or Meta. That was the choice of the people above him.” — lapcatsoftware@mastodon.social

📱 Apps & Services {#techhistory #rss}

1️⃣ Can you imagine that Adobe made the Photoshop 1.0 source code available to the Computer History Museum! I remember testing Photoshop back in the day on the Mac (I can't remember exactly which one it was, though). I remember thinking at the time that the app wasn't obvious to use. Of course, we all had MacPaint as a reference, but Photoshop was quite up there. It never really clicked with me. 2️⃣ I'm sorry, but the current Mac desktop under Tahoe is already too hard to comprehend for putting holiday lights everywhere. Nice try, Festivitas, I’ll pass. I admire this developer's creativity and guts, though. 3️⃣ I know, I already mentioned RSS reader apps, but here’s another one: Today—an RSS feed for the modern age. It apparently uses some on-device AI (from the developer himself: “if you’re curious about the technical details, I built Today using SwiftUI and SwiftData, with Apple’s NaturalLanguage framework powering the local AI features. The whole project is a love letter to both RSS and native iOS development.” I installed it and played with it a bit, but it's not a game-changer—oh, and that app icon, soooo 1999. I'll pass. 🙈 4️⃣ I agree with most of Manuel Moreale’s thoughts on MCP servers. There is a big chance for new gatekeepers, new middlemen. Here's a quick definition of MCP servers and their purpose: MCP (Model Context Protocol) servers are standardized interfaces that enable AI assistants like Claude to securely connect to external tools, data sources, and services. Instead of requiring custom integrations for each application, MCP provides a common protocol that acts as a bridge, enabling AI to access databases, interact with APIs, retrieve information from your existing systems, and perform actions such as creating tasks or updating records.

🚧 Special projects {#learningexperience #n8n #automation}

1️⃣ I'm officially an n8n user! I've been learning this automation platform recently, and boy, I'm excited about it. So far, I have two working workflows, but I have tested quite a few other integration tidbits with services like RSS, Inoreader, Discord, Telegram, Claude AI, etc. I find the learning curve to be quite steep, but I'll make it. I have a ton of workflows that I'm thinking of putting together. I expect 2026 to be the year of automation projects. If you don't know what n8n means: it's like visual programming or low-code-no-code programming.

📺 YouTube {#apple #uidesign #tech #techhistory}

1️⃣ People are getting older and Apple’s executives are no exception. This video reassured me about what is going on at Apple recently. 2️⃣ Are we stuck with the same desktop interface that we have been facing since the early days of the Mac? In this video, this experienced designer thinks we are in a status quo era. 3️⃣ Segway will soon sell an eBike. From this teaser video, I'm not impressed. Looks like a normal bike to me. More on January 5th. 4️⃣ Did you know that Expo 67 is still the most attended universal exposition of all time? Yep! This documentary recounts many things that I wasn't aware of. What a marvellous era. I'm not sure if we could do this type of project today. Could we? 5️⃣ Get a peek at the iPhone Ultra, the first foldable smartphone from Apple. It's not the real thing, only a mockup.

“Expo 67 was a World’s Fair held in Montreal in 1967 to celebrate Canada’s centennial, themed “Man and His World.” It showcased global innovation, architecture, culture, and technology through bold national pavilions and futuristic ideas, emphasizing human progress, cooperation, and optimism about the future. Widely regarded as one of the most successful world expos ever, Expo 67 had a lasting impact on Montreal’s international profile, urban development, and cultural identity.”

🔮 Looking forward {#foodforthoughts}

1️⃣ This is the last edition of the ephemeral scrapbook newsletter for 2025. What a ride! I'm eagerly looking forward to next year, but with moderation. A dear friend of mine once told me, “The man who always looks ahead with enthusiasm has passed away.” Or something like it. You get the idea. I will gently savor the last few days of the year, I promise. 2️⃣ Is Microsoft too forward-looking? Maybe. See below for yourself.

🌟 Miscellaneous {#ai }

1️⃣ About this edition's header image: the result of a prompt to ChatGPT to create an image of a retro-style seventies look of a 2025 calendar. If you pay attention, you'll see many issues with the results. To me, this funny image perfectly summarizes the state of AI in 2025. 😂 2️⃣ Since macOS Tahoe, I’ve been experiencing screen flickering on my Apple Studio Display and my MacBook Air. When I first encountered it on the Studio Display, I thought it was a hardware issue. But when it started to occur on my MacBook Air, it couldn't be a hardware fault. I began to think about possible Liquid Glass rendering issues. A reboot will fix the problem for a while, but it will come back. Thankfully, I'm not alone; many people are reporting the same problem, as Michael Tsai noted in this post.

"RSS offers a simple, durable way for publishers to keep control of their distribution and for readers to keep control of their attention." — Ben Werdmuller

👉🏻 Main 🌟 Meta 🌟 Blips 🌟 Blog 👀

I wish you a great week! ✌️ 🇺🇦 🇨🇦 🇪🇺 💪🏻

https://notbyai.fyi

I've been saving articles lately that all share an uncomfortable feeling: disconnection. Not burnout—disconnection. The difference matters.

Burnout is temporary, recoverable. You take a break, touch grass, come back refreshed. Disconnection is deeper. It's the slow realization that the thing you once loved has fundamentally changed, and not in your favor.

Riccardo Mori nailed it in November: "Technology's evolution from empowering tool to profit-driven, hype-driven ecosystem has left long-time enthusiasts feeling disillusioned, disconnected, and increasingly skeptical of an industry that now seems to serve itself more than its users."

The Shift Nobody Wanted

Somewhere along the way, tech stopped being a tool we wielded and became a system that wields us. This wasn't an accident. It was a business model optimization.

The clearest example? Social media. Charlie Warzel's piece on X as a "worthless, poisoned hall of mirrors" isn't hyperbole—it's careful documentation of what happens when a platform's incentives completely divorce from user value. These services were supposed to connect us, facilitate conversations, democratize information. Instead, they became engagement machines optimized for advertiser revenue and whatever keeps us scrolling, regardless of the psychological cost.

Twitter used to be where you found your people. Now X is where algorithms decide what enrages you enough to stick around. The transformation is complete, and it's repulsive.

The AI Benchmark Circus

AI took the same path, just faster. We're drowning in announcements about which model scored 0.3% better on some synthetic benchmark nobody actually uses. Meanwhile, the actual user experience—the thing that matters—gets treated as an afterthought.

Federico Viticci pointed this out in November: what differentiates AI products now isn't raw capability, it's the experience wrapped around that capability. But here's the thing—experience for whom? The companies need you locked into subscriptions, feeding their models with your data, accepting whatever interface they deign to provide. They're optimizing for their business metrics, not your actual needs.

The benchmark obsession is a distraction. It lets companies compete on numbers while ignoring whether their products actually improve anyone's life.

What We Actually Lost

Remember when tech felt like it was for something beyond quarterly earnings?

RSS feeds that let you read what you wanted, when you wanted, from sources you chose—without an algorithm deciding what you "should" see. Software you purchased once and owned, rather than rented month-to-month with features that could vanish in the next update. Platforms that didn't require constant feeding with personal data just to function at a basic level.

That web wasn't perfect. But it had a fundamentally different relationship with users. Tools were designed to empower you to do something. Now they're designed to keep you engaged, monitored, monetized.

The shift from ownership to access meant we stopped being customers and became inventory. Your attention is the product being sold. Your data is the raw material being refined. The actual service? That's just the vehicle for extraction.

Every Interaction, Intermediated

Here's what gets me: you can't just do things anymore. Every interaction has to run through someone else's infrastructure, someone else's algorithm, someone else's business model, someone else's terms of service that change whenever convenient.

Want to share photos with friends? That's not just hosting files anymore—it's feeding Facebook's or Instagram's engagement metrics. Want to publish your thoughts? Medium wants to paywall them and take a cut. Want to message someone? iMessage, WhatsApp, Signal, Telegram—each one another walled garden, another platform hoping you'll bring all your contacts with you.

The promise was connection. The reality is fragmentation controlled by intermediaries who profit from your inability to leave.

The Hype Cycle Ate Everything

And then there's the relentless hype. Every minor iteration gets breathlessly announced as revolutionary. Every feature gets a marketing name and a keynote slide. Every change gets framed as innovation, even when it's just a new way to extract value.

Remember when we got excited about technology because it genuinely expanded what was possible? Now we're exhausted by an industry that discovered it's more profitable to promise the future than to deliver the present.

The AI boom is the apotheosis of this. Fundamental questions about utility, ethics, environmental cost—all drowned out by investor excitement and billion-dollar valuations for companies that haven't figured out sustainable business models beyond "charge enterprises a fortune and hope."

Why the Enthusiasts Are Leaving

The people checking out aren't technophobes. We're not afraid of change or nostalgic for some imaginary golden age. We're the people who built this stuff, who championed it, who got others excited about it, who believed in its potential.

And we're watching it curdle into something unrecognizable.

The disillusionment isn't about the technology failing. It's about realizing the technology is working exactly as designed—just not for us. We're not the beneficiaries; we're the resource being harvested.

That's the disconnection Mori described. When you realize the thing you loved has been optimized for someone else's benefit, and your role is just to keep feeding the machine.

What Now?

I don't have a tidy answer. "Vote with your wallet" doesn't work when the entire industry has converged on the same exploitative models. "Build alternatives" is noble but exhausting when you're fighting trillion-dollar network effects.

What I do know: naming the problem matters. Recognizing that your discomfort isn't personal failure or inability to keep up—it's a rational response to a system that's stopped serving you.

The tech industry wants you to believe the only path forward is more—more AI, more platforms, more subscriptions, more integration, more data sharing. But maybe the actual path is less. Smaller tools, more ownership, fewer intermediaries, more intention about what you let into your life.

We didn't sign up to be monetized. We signed up to be empowered.

It's worth remembering the difference.

Here is my personal year in review for 2025. This year, I’ll use a different style and structure. Let’s start with a few notable milestones and observations across the year.

Sat, Jan 25: In late January, I began feeling exhausted from using Slack to monitor the Craft community, so I chose to take a break. I'm very invested in anything related to Craft, but taking a step back can be salutary.

Sun, Mar 9: I officially switched from HEY Mail to Fastmail. I knew it was coming. This project took me about a week to complete which is much faster than expected. It's part of my journey to digital sanity. I wrote “Migrating from HEY Mail to Fastmail: My Guide For a Smooth Transition” blog post.

Fri, Apr 18: Lately, I've been finding it challenging to produce YouTube videos. I'm unsure how to break out of this period of uncertainty. My videos are closely linked to Craft and its development. The absence of significant changes or meaningful updates is having an effect.

Sun, May 4: I'm finally committing to building websites using Realmac software Elements. It's been a while since I learned a new app, the last time being Craft in late 2020. Although I'm not a professional web developer or designer, Elements makes the process approachable. I'm not beginning from zero; instead, I'm using my existing personal landing page as a reference.

Wed, Jul 30: I've finished my new website (https://whois.numericcitizen.me). Moving forward, my focus is on maintaining it and adding new content. Creating YouTube videos is impossibly hard because I'm rarely at home and don't have access to my video production equipment. This partly explains why I don't produce new videos frequently.

Sat, Nov 22: Well, it seems that 2025 was a fairly quiet year! Or was it?

Thu, Dec 4: My YouTube video production flow is back on track. I made several videos in the last few weeks, and I still have many subjects and angles that I want to explore for new videos. The outlook for next year looks favorable.

Sun, Dec 14: Time is running out. Only two weeks left for the end of the year. This review isn't done yet because I fell into the n8n rabbit hole. I'm super excited for this automation platform. I feel it's going to be my new digital playground in 2026.

Wed, Dec 17This is not a significant milestone per se, but it's notable: I got rid of my IFTTT account after more than 5 years of using the automation service. I found a way to replace IFTTT with one of Micro.blog's lesser-known capabilities. Closing my IFTTT means the money saved will help partly pay for the future n8n instance on DigitalOcean.

Last year’s predictions in my 2024 year in review:

For 2025, I want to focus even more. I want to be more intentional. I want to continue developing The Craft Bible with more content. I want to produce more videos for my YouTube channel. I also want to spend more time making the Ephemeral Scrapbook newsletter. This means spending more time reading and gathering interesting information tidbits. Lastly, Micro.blog will continue to be my go-to place for the social web and microblogging, but I expect my Bluesky usage to increase and find an even more prominent place in my digital landscape.

How did I do in 2025? Well, I was much more intentional, but I didn’t expand The Craft Bible as much as I wanted or produce as many YouTube videos as I’d hoped. As I follow the development of Craft to contribute to those two areas, there was a relatively quiet period in mid-2025, so I didn’t have enough material to support my ambitions.

The one thing shining for 2025 is the continuation of the Ephemeral Scrapbook newsletter, with 25 editions. I’m proud of this accomplishment because I kept doing it at a regular pace. How many more subscribers did I get? Well, a few more, but I lost some, too. I know I shouldn’t care about this.

Another project of mine is creating a mini website about Apple’s Liquid Glass UI visual language. I was very active updating the content during the summer after each beta releases until the official launch in September. For the rest of the year, things slowed down. I plan to keep that project alive for as long as Apple maintain Liquid Glass. Next year could reserve a few surprises since Alan Dye, the leading proponent of Liquid Glass, no longer works at Apple.

I also find satisfaction in having learned how to use Realmac Software Elements to build my new personal landing page from scratch, which is available at whois.numericcitizen.me. It’s uncommon these days to pick up a brand new app and begin learning how to use it for a specific project. I’m far from an expert, but I know enough to create the website that I had in mind. Although the content and design of the landing page will likely change over time, the basic structure is solidly in place. That is my second most satisfying accomplishement for 2025.

Regarding my use of Micro.blog and Bluesky: Micro.blog remained central to my digital social interactions, while Bluesky played a minor role. I continued to use it throughout the year, but not as frequently as I had expected. I kept cross-posting everything from Micro.blog to Bluesky (and Mastodon) and got a few replies from Bluesky users. My enthusiasm for this alternative social platform gradually diminished, no longer matching the peak moments I experienced with Twitter. And it’s probably the best outcome I could imagine, given my goal to focus more.

I briefly revisited Medium and tried to share some articles there, but it didn’t meet my expectations for attracting people interested in work-related and career topics. I stopped using it in August. Although I haven't gone back to Substack, I checked the platform a few times but stayed away, which shows I stayed focused and avoided distractions.

From an applications-and-services usage perspective, I made some important decisions, too. I dropped Readwise and Timings (the Mac app), but doubled down on AnyBox. I left HEY Mail for Fastmail. I published two content creation workflow updates reflecting those changes, one in March and one in November. These publications are less frequent, reflecting a more settled state of my digital toolbox.

A few words about photography: it’s primarily a travel-related activity. The more I travel, the more I dedicate time to it, but it shouldn’t be like that. There should be ways to create shooting opportunities, yet my other digital hobbies tend to take priority. It’s an ongoing challenge. However, I’m optimistic: next year I plan to visit Egypt, France, and Thailand, which should keep me sufficiently occupied.

What’s up for 2026?

I plan to keep prioritizing what is best for me, whether online or in my personal life. I will steer clear of major distractions and focus on enhancing what I already have. One small project I want to do is redesign the content creation workflow diagram that comes with my workflow articles using Apple Freeform. My current use of Keynote constrains the diagramming space, but Freeform’s limitless canvas would be very beneficial. I’ll wait for the next update to start this process. It’s a very small project, but something that I’m looking forward to; Freeform is so nice to use. It’s one of the best Apple software in years.

Craft remains a key part of my digital toolkit and might even become more important. This could lead to more Content related to Craft for The Craft Bible and my YouTube channel. As 2025 ends, I’ve begun testing Claude, MCP, and agents using a beta version of Craft Agents. I’m truly impressed by the capabilities of modern software and AI, with no programming needed. Exploring Craft, AI, and agents could be an exciting area to delve into alongside the n8n automation platform.

That is all, guys. See you in 2026 for the next year in review report.

Enabled the RSS feed in the News section of “Who is Numeric Citizen” website.

Recent readings about n8n and with the help of Claude AI, I finally found a way to replace IFTTT for archiving my RSS feeds content: it won’t be by using an n8n automation but a simple feature that was sitting right in front of my eyes on Micro.blog: cross-posting. The trick is simple: each of my RSS feed is added to the Sources panel in Micro.blog, from there, I configure cross-post the RSS feed article to other places like Day One journal using email-to-dayone. Voilà. I’ll be closing my IFTTT account later today after so many years of service. The only rather big downside: Micro.blog doesn’t copy images from the source into Day One while IFTTT could. 🫤

Update #1: I submitted my issue on the Micro.blog help forum, and a few hours later, a fix was on the way. Thanks @manton

Update #2: And now it is available; photos are now supported, too! Thanks to Manton!

👤 Personal {#creativity}

1️⃣ I might have found the right creative beat by alternating between creating a YouTube video and a new edition of the Ephemeral Scrapbook newsletter. I shouldn't try to do both during the same week, it's way too much. 2️⃣ I made another change with this newsletter edition. I decided to support the “not by AI” movement. You'll see a small badge at the bottom, along with a link to learn more about the movement and why it is essential. The rule is that at least 90% of the content must be human-made. I'm easily crossing that threshold. I discovered this initiative through this website, I like the idea but their version of the logo, not really.

🗺️ Discoveries {#web #fediverse}

1️⃣ Ghost is relaunching Ghost Explore, a place to discover other blogs and websites hosted or running on the Ghost platform. It's a great way to be discovered and to find new places to explore (pun intended), too. By moving towards the Fediverse, Ghost kind of had no choice but to augment its platform with a discovery mechanism. 2️⃣ Explore 6,000 years of battles, inventions, philosophers and more... on an interactive 3D globe. It's super cool. That's the web that I like. 3️⃣ Dealgorithmed and disassociated.com both seem to aim for the same mission: to help people stay out of platforms and enjoy the web as it should be. I'm subscribing to both. 4️⃣ It appears that TinyGlade can be played on the Mac via GeForce NOW! I saw a post on my Micro.blog timeline about that. That's something that I could try during the upcoming holidays!

👨🏻‍💻 Writing {#yearinreview}

1️⃣ It's that time of year to take a look back at my year as a blogger. This year, although I kept a journal of my highlights, I must admit that 2025 was relatively quiet. Yes, I could say that 2025 passed like a long, peaceful river. Writing this review should be pretty quick, especially since I plan to change my approach to get a different kind of review than last year's. Stay tuned.

🌄 Photography {#mood #source/reddit #source/unsplash}

1️⃣ The end of autumn and winter is the time of year when I am the least active in photography. I live in a rather big city in Canada (Montreal, as seen in the header photo), a cold, gray country in winter. I know it's still a source of beautiful images, but this climate and the discomfort it brings me are enough to take a break. Maybe it's time to focus my energy on cleaning up my thousands of photos; who knows, I might come across a gem or two to share with you. 2️⃣ Reddit contains not only rage and controversial threads, but you can find a few gems like this one posted by users like u/unlicensedlensed, it's foggy out there | Munich. Great B&W images.

🍎 Apple & Tech {#tech, #stevejobs}

1️⃣ Thanks to a shared memory by Scott Knaster on his Substack, I didn't know Steve Jobs had the idea of an all-glass headquarters a long, long time ago. 2️⃣ The tech world is moving fast, and it can be exhausting. Actually, it is exhausting. But is the tech world moving in the right direction? Because we cannot have an iPhone moment every year, it seems that more than ever, the tech world is surfing on hype. If tech companies don't deliver, we might feel betrayed because we're constantly tricked into some marketing traps. Trust is eroding. For Riccardo Mori, that's precisely what happened in the last two decades. His piece is an excellent recap of what actually happened. Well worth the read. 3️⃣ Alan Dye, the guy in charge of design at Apple, left. He will join Meta. Stephen Lemay, a 26-year Apple design veteran, will take over the role from Dye. Alan Dye is a controversial figure in Apple's design space. Some pundits will say that he isn't really a designer. Now, it's time to look ahead and see how Apple will evolve. Liquid Glass is controversial, probably not as much as the iOS 7 redesign was, but it is nonetheless polarizing.🏃🏻‍♂️‍➡️ 4️⃣ But that's not all, two other execs are retiring, enough to warrant a press release. A few years ago, Apple ran a marketing campaign in which it announced a new product each day for a whole week. This year, it's different: Apple announces an exec departure once a day for the whole week.🤷🏻‍♂️ You can visit the current Apple Leadership page right here.

“Firstly, I maintain that it makes absolutely no sense that Alan Dye has the power he has, because he simply has no taste. But what’s worse is that he wields that power so clumsily, so carelessly. And because it goes unchallenged, unchecked by someone higher than him, the entire industry suffers the consequences.” — John Gruber, quoting Louie Mantia on his recent post following Alan Dye’s departure from Apple. Ouch.

📱 Apps & Services {#anthropic #claude #chatgpt #craft/mcp #rss}

1️⃣ In a recent post by MacStories, they argue that since LLM models are mature enough that most people won't actually see the difference in performance, the attention is now turning to the user experience. For example, consider how you configure an MCP connection in ChatGPT versus in Anthropic's Claude. The latter is much easier to do. The look and feel of the Claude Mac client feels better than ChatGPT's. I decided to give Claude a try for one month to experiment with Craft MCP connections to portions of my content. 2️⃣ The CEO and founder of Ghost, John O'Nolan, recently shared that he is working on a new RSS feed reader called Alcove. Another RSS feed reader, you might wonder? Yep. Another one. What strikes me about this announcement is that he used x.com to share his article. As Ghost adopted Fediverse this year, you might wonder why bother with x.com! Actions speak louder than words for me.

🚧 Special projects {#craft/mcp}

1️⃣ I made a few changes to my projects page on my landing page. I'm slowly gearing up to plunge into the consumption of Shortcuts and Craft APIs. The only missing things: spare time and patience, because I'll need a lot of both, especially with Shortcuts editing, which is far from an enjoyable experience. 2️⃣ I found a use case for MCP and Craft, and I’ll document it in a separate document so that I can submit my use case to the winter challenge the Craft team put together. In summary, I'll use Claude to prompt my Craft daily notes via an MCP connection to build a year-in-review summary. For 2025, the review will be incomplete because I restarted using Craft daily notes in October. But for next year, if all goes according to my plan, I should have a more complete journal.

📺 YouTube {#iphone #ipad #macintosh}

1️⃣ What if a robot could help benchmark iPhone performance? That's exactly what was done in this video. 2️⃣ Even with this year's additions to iPadOS, the iPad is still a rather limited device compared to the Mac. This video explains the three main reasons. Just a reminder: iPadOS's roots are much closer to iOS than to the Mac. 3️⃣ Do you often reboot your Mac? Do you like the booting sound coming from the speakers each time the Mac reboots? I do. Here's a short video explaining the audio science and a little bit of history about the Mac startup sounds.

🔮 Looking forward {#apps #rss}

1️⃣ I want this (YouTube video about Apple's Digital ID) to come to Canada ASAP! But, it will take a long time before we can leave our wallet at home if Matt Birchler's experience is any indication. 2️⃣ Certainly looking forward to Alcove, a new RSS reader by the CEO and founder of Ghost. 3️⃣ I’m looking forward to seeing the winners of the winter_challenge organized by the Craft team. I shared my submission, which I think fits really well with Craft's mission: being a good app for writers and thinkers like me. You can see that in action in my latest YouTube video.

🌟 Miscellaneous {#socialnetworks}

1️⃣ What's going on in Musk's head? Maybe we should look at X's current state to get an approximation. The article from The Atlantic (paywall might apply) argues that X’s new “About This Account” feature—meant to improve transparency by revealing account origin, location, and username-change history—has instead exposed the massive scale of misinformation, foreign influence, and deception on the platform. The feature instantly revealed that many seemingly “patriotic” American accounts are actually operated from abroad, while also mislabelling some legitimate users, further confusing matters. The result is a chaotic environment where authenticity is impossible to verify, fake personas amplify political narratives, and X’s architecture incentivizes performance over truth, turning the platform into a dysfunctional information ecosystem detached from reality. Best thing to do? Log off and delete. You'll see there is life after Twitter. 2️⃣ Once you log off for good from Twitter / X, you'll discover that there is a world awaiting you, away from platforms, away from manipulation and rage. Just ask Greg:

“When there was one big platform, leaving meant missing out. Now there's Mastodon, Bluesky, Threads, and whatever else springs up next week. No single space feels needed anymore. The FOMO vanished. Once that happened, having your own blog stopped looking like the odd choice.” — Greg Morris

👉🏻 Main 🌟 Meta 🌟 Blips 🌟 Blog 👀

I wish you a great week! ✌️ 🇺🇦 🇨🇦 🇪🇺 💪🏻

https://notbyai.fyi

Some believe that using AI for writing articles is lazy, not creative, and that you don’t earn the credit for doing it. I disagree. Or, it depends. Here’s a personal experiment.

This week, I shared an article about digital sovereignty with my professional network on LinkedIn. Even if I used ChatGPT to write the article, I spent days on it, or, more specifically, I spent days creating and testing different prompts. The article was written in French, then later translated into English and shared on my blog (see “On Digital Sovereignty and Strategic Realism”).

In this meta blog post, I want to share the final prompt that led to the article. Please note that the final response from ChatGPT was manually modified before being posted. Here’s the prompt below followed with some comments.

I would like you to write an article of no more than 1500 words on the topic of digital sovereignty, a subject that is currently highly relevant both in Québec and around the world. This article will be read by information technology and cybersecurity professionals. It should offer a clear-eyed perspective on the issues and challenges related to the pursuit of digital sovereignty for organizations and governments. The article should not be alarmist, but realistic and critical, with the goal of prompting reflection among readers.

Here is how the article should be structured: an introductory section that provides context, followed by a section explaining why digital sovereignty is essential but not a fully realistic target in absolute terms; we must remain pragmatic. Then, a section offering potential solutions or realistic strategies that large organizations should adopt, especially if they are critical to society.

The article should conclude with open questions inviting readers to reflect and comment in order to spark a constructive conversation. Use the following elements to build the article. Reuse the provided links as references.

• Over the past five years, a series of international, political, and technological events has forced us to examine the notion of digital sovereignty (a few examples: the rise of the GAFAM giants, the Snowden affair, the U.S. Patriot Act and Cloud Act, recent U.S. elections, mergers and acquisitions in the tech sector, etc.).
• What exactly is digital sovereignty? “Digital sovereignty refers to the ability of a state, an organization, or an individual to control and manage its data, digital infrastructures, and technologies in order to ensure its strategic autonomy and security in the digital space.”
• It is the ability to fully exercise one’s rights and choices in the digital domain without being subject to external constraints.
• Major outages from several cloud service providers have occurred, the most notable being:
• AWS (October 20, 2025: Revealing the Cascading Impacts of the AWS Outage – Ookla)
• A Microsoft Azure outage (October 29, 2025: Microsoft Azure Outage: How the World’s Second-Largest Cloud Platform Went Down – ThinkCloudly)
• And more recently, a Cloudflare outage (November 18, 2025: Cloudflare outage on November 18, 2025)
• Another outage occurred last year, on July 19, 2024, when a problematic update from CrowdStrike caused widespread service failures (2024 CrowdStrike-related IT outages – Wikipedia)
• These outages strongly remind us of our deep dependence on cloud services and technology in general, both personally and within organizations.
• We need to reflect and attempt to find viable answers and strategies to these questions: Are we well prepared? Do mitigation solutions exist? Is digital sovereignty only about data?
• Is digital sovereignty a mirage? Are we not always dependent on something beyond our control? We must keep in mind that:
• Complexity and cost: Developing sovereign solutions (cloud, software, artificial intelligence) requires massive investments.
• Global interdependence: Digital value chains are globalized, making total autonomy difficult, if not impossible.
• Risk of protectionism: Some fear that digital sovereignty could be used as a pretext for trade barriers.
• Clearly, digital sovereignty is not merely about using or not using cloud computing, or choosing which cloud to use; it is much broader than that.
• I really like this quote, and it must be integrated into the article: “Digital sovereignty is neither a luxury nor a technological gimmick. It is a pillar of resilience and democracy.” — Le Devoir: https://www.ledevoir.com/opinion/chroniques/936699/parlons-souverainete
• I believe we need to accept the fact that we will never have full control over our digital destiny. Therefore, we must adopt mitigation and exit strategies to reduce dependency links.
• We must maintain a message of independence toward major industry players so that they understand they are not alone, even if they are powerful. We need to be strategic, give ourselves the means to stay agile, and diversify.

As you can see, the prompt is nearly as long as the final product. It took me a dozen tries to see what ChatGPT could create. After each try, I would modify and add instructions to the prompt. Oh, and I searched for references myself. In short, this was a multi-day effort. Am I a lazy guy? You tell me.

As an IT professional, I like to reflect on specific issues that can have big impacts on organizations and society. This article was first written in French and shared with my professional network on LinkedIn.

Digital sovereignty has, in just a few years, become a central issue for governments, enterprises, and even individuals. Long confined to academic debates, the concept has now become a strategic concern in light of an undeniable reality: our growing dependence on global digital infrastructures.

Recent events illustrate this vulnerability. The rise of the GAFAM giants, the revelations of the Snowden affair, the implications of the U.S. Patriot Act and Cloud Act, and the alleged interference in U.S. elections have all highlighted the risks associated with the concentration of digital power. Added to this are far more concrete technical incidents:

• AWS outage – October 20, 2025 (details)
• Microsoft Azure outage – October 29, 2025 (details)
• Cloudflare outage – November 18, 2025 (details)

Not to mention the problematic CrowdStrike update in July 2024, which crippled critical services in banks and airports (Wikipedia, among other sources).

These events are not anecdotal: they reveal a systemic dependence affecting our organizations and, by extension, individuals. The question is no longer “Should we be concerned?” but rather “How do we prepare?”

Why Digital Sovereignty Is Essential

Digital sovereignty is defined as “the ability of a state, an organization, or an individual to control and manage its data, digital infrastructures, and technologies in order to ensure its strategic autonomy and security in the digital space.” It involves the ability to exercise one’s rights and choices without external constraints.

This autonomy is critical for three key reasons:

Security and resilience: Data is a strategic asset. Exposure to foreign jurisdictions can create legal and operational risks.

Decision-making autonomy: Without control over infrastructures, room for maneuver during crises is severely limited.

Preservation of democracy: As Le Devoir aptly states:

“Digital sovereignty is neither a luxury nor a technological gimmick. It is a pillar of resilience and democracy.”

However, seeking total autonomy is unrealistic. Digital value chains are globalized, and the costs required to develop sovereign solutions—cloud platforms, AI systems, software—are immense. Moreover, an overly protectionist approach could hinder innovation and harm competitiveness.

Pragmatism and Strategies

We must accept a core reality: we will never have full control over our digital destiny. Global interdependence is structural. Rather than pursuing absolute independence, we should take a pragmatic approach focused on reducing risks and diversifying dependencies.

This approach requires concrete strategies, along with significant time, financial investment, human resources, and strong governance. Digital sovereignty is not a quick fix; it is a long-term strategic initiative. And it extends far beyond saying “we’ll choose this local cloud provider for our organizational needs.” It is much deeper and more complex.

Key Measures for a Strategy Aimed at Greater Digital Sovereignty

• Diversify providers to avoid overreliance on a single cloud player. Diversification reduces systemic risk related to outages or contractual disruptions.
• Strengthen contractual clauses to include exit mechanisms and data portability requirements. A clearly defined exit strategy is essential for preserving flexibility.
• Hybridize infrastructures by combining public cloud, private cloud, and on-premises solutions. A hybrid approach allows organizations to retain control over sensitive data while benefiting from the scalability of major providers.
• Invest in skills to operate hybrid and multi-cloud environments. Digital sovereignty depends as much on technology as on the expertise of the teams managing it.
• Adopt open and interoperable standards wherever possible to reduce technological lock-in (the notorious vendor lock-in) and facilitate system and data portability.
• Enhance local cybersecurity by deploying sovereign solutions for critical functions such as authentication and encryption.
• Participate in regional initiatives such as sovereign cloud projects in Europe or Québec to pool efforts and investments.

These measures will not provide total sovereignty, but they significantly reduce vulnerability and increase resilience. They also send an important and necessary signal to major industry players: organizations are not condemned to absolute dependency.

Open Questions for Reflection

Is digital sovereignty an achievable objective, or a strategic mirage? Are we ready to invest heavily to reduce our dependencies? How do we reconcile economic openness with digital autonomy? And above all: what degree of sovereignty is truly necessary to safeguard resilience and democracy?

👤 Personal {#newsletter}

1️⃣ I'm sorry if this edition is late. I was on vacation for a week and didn't gather enough content to put together a new edition until recently. 2️⃣ I have also been busy recently testing a new version of Craft, which required more of my time than usual. This version is a significant shift, which prompted me to allocate more of my free time than usual. Things should return to normal once this version is out.

“When the things that matter most become monthly fees rather than assets, our relationship to society changes.” — Jenna Park in “America is one big subscription service”

🗺️ Discoveries {#apple #applerumor}

1️⃣ This could be the best and most surprising video of the year! Discovered on Mastodon, available on YouTube! This guy has a lot of talent, that’s for sure. It's a fake Apple Event happening in March of next year, announcing already heavily rumoured products. I'll let you watch yourself. I wonder if Apple has become too predictable, which allows people to create these videos. 2️⃣ I discovered a new blog: disassociated—a great article about a possible (and desirable) comeback of personal blogs. I certainly hope so.

👨🏻‍💻 Writing {#aiwriting}

1️⃣ iA Writer has introduced a new feature called Authorship that visually distinguishes AI-generated text from human-written content, allowing users to identify and improve upon AI contributions in their documents easily. The implementation is simple yet effective, if demo clips are any indication. It's the first instance of such an idea I've seen. I wish Ulysses would do something like that. 2️⃣ As reported by CBC, Alberta is considering using AI to write a new law. Yep, you read it right. What can go wrong you might say? This is the first known occurence of such stupid idea.

🌄 Photography {#iphone #unsplash #creativity}

1️⃣ In “Becoming an iPhone Photographer”, Lee Peterson reflects on his diminishing use of his mirrorless camera while using the iPhone more. This gradual change enabled him to be more careful and appreciative of his iPhone as a camera, thereby providing greater flexibility. 2️⃣ A reflective exploration of whether AI can create meaningful art, arguing that true artistic value still depends on human intention and interpretation, by Robert Adams. 3️⃣ Finnish photographer Juha Tanhua creates striking “space-like” images by photographing gasoline and oil puddles in parking lots. Although the photos resemble astrophotography—galaxies, nebulae, comets—they are captured by pointing the camera downward at iridescent spills on asphalt, often after rain. Tanhua has pursued this project since 2005, treating these puddles as a hidden microcosm and later enhancing contrast to emphasize their cosmic appearance. 4️⃣ The Unsplash Awards, 2025 edition, is full of gems. The architecture category is always my favourite but most categories contain great and sometimes touching images. That's why photography as art exists: for touching people.

🍎 Apple & Tech {#macintosh #applesilicon}

1️⃣ Recently, Apple Silicon crossed the fifth anniversary mark. Here's a good comparison between an M1 and an M5 from MacRumors. What a ride, and I get the feeling that Apple is far from done with this processor. Apple Silicon is probably the most profound enabler of any transformation the Mac has undergone since its inception. More from MacSparky. 2️⃣ Apple has big plans for the Mac in 2026, but it appears that the Mac Pro might not be part of them. 3️⃣ Apple invited some developers to share their story about adopting Liquid Glass for their apps. My experience, as documented here, is that the outcomes of Liquid Glass adoption vary quite a lot—great examples include Craft and Ulysses. 4️⃣ Backblaze’s Q3 2025 Drive Stats report reveals an overall annualized failure rate of 1.55% across 328,348 drives. That's a lot of drives. Interesting to see drive stats by brand and sizes. This could influence my buying decision if I were to replace drives in my Synology NAS. 5️⃣ I love ChatGPT Atlas even more since they released an update that adds vertical tabs, just like the ARC Browser. But Microsoft might be wrong with its approach to AI with Edge. I don't really like Microsoft Edge, and I don't really like Copilot in general because I've been forced to use it at work, and it's not impressive. They use ChatGPT services in the back-end, but somehow Microsoft manage to create an inferior experience compared to ChatGPT. 6️⃣ Apple's macOS Tahoe icons are a departure from Mac history. As for iOS, the trend goes downhill. Most of the new icons represent a decline in design quality. John Gruber feels rather critical about that, too. The Safari icon, before and after. It's not an improvement. 7️⃣ Is the lack of Windows support on Apple Silicon Macs hurting Apple after 5 years? Well, I don't think so. I guess I changed my mind. What is hurting the Mac is the Electron development framework and web technologies, because fewer and fewer developers are using Mac-native APIs and prefer multi-platform toolkits.

"The first five years of Apple silicon are now the five best years in the Mac’s history." — Jason Snell in “How five years of Apple silicon transformed the Mac”

“iPadOS has got more feature improvements in 26.1 and 26.2 than the entire previous three years of Stage Manager” — Steve Troughton-Smith on Mastodon

🚧 Special projects {#craft #mcp}

1️⃣ I've been spending quite some time reorganizing a vast portion of my content in Craft to better take advantage of Craft’s upcoming APIs and MCP support. I created a large collection of all the video production documents, which allowed me to prompt my collection for metrics like average video duration (collection can’t summarize columns or properties yet). And sure enough, the Craft Assistant returned with a valid answer! 2️⃣ Speaking of MCP, did you know that the Day One journaling app on the Mac supports MCP? Here's the documentation.

📱 Apps & Services {#apps}

1️⃣ Apple announces finalists for the 2025 App Store Awards. Besides Acorn, an image processing app, I don't know any of these apps. To me, this year's selection is meagre. 2️⃣ According to an Apple-commissioned study, the EU’s Digital Markets Act didn't bring down app prices. Who knew! 3️⃣ Folder Quick Look is a macOS app that you must install right now. Preview folder and archive contents (ZIP, RAR, and more) instantly in macOS Quick Look. Just select a folder and press the Space bar. Version 1.5 added support for image thumbnails if the folder contains image files. See the following screenshot: a folder called “background images" is previewed.

📺 YouTube {#stevejobs #bloggerlife #design}

1️⃣ Great and unpublished until recently interview with Steve Jobs, in the early days of Pixar. This guy had so many great insights. 2️⃣ Tiago Forte needs a break—a short video from him explaining what's going on for him in the next few months. 3️⃣ Apple calls it the 'Spinning Wait Cursor.' We, the users, call it the Spinning Beach Ball of Death—an interesting story behind this iconic UI element of the Mac.

🌟 Miscellaneous {#tech #ai}

1️⃣ CloudFlare’s major outage is one of many from internet hyperscalers recently. They didn't wait long to explain what happened and offered their apologies. I read most of the text, and as John Gruber said, it's the best way to address this public relations nightmare. More than ever, those failures show how dependent we are on internet technologies. 2️⃣ I see a trend where more and more people are using on-device LLM for their generative AI use cases. These LLMs require a significant amount of memory and processing power. My next MacBook and iPad Pro upgrade will undoubtedly take this into account. MacStories tested the latest M5 iPad with a local LLM and found that Apple’s claims about the upgraded neural engine are valid. The M5 iPad Pro (or M5 MacBook Pro) is a powerhouse for running local LLMs. More details and charts here. 3️⃣ This newsletter could have been called “The Ephemeral Digital Garden". 4️⃣ For this edition, I made a tweak: tags are now part of each section's header between {}. Please tell me if you prefer it that way. I do.

🔮 Looking forward {#weather #ai}

1️⃣ I always wondered how artificial intelligence techniques could help weather forecasting. People tend to see weather forecasting based on large mathematical models being run on powerful computers. Things might be changing, thanks to Google's WeatherNext 2, a Google DeepMind model. Forecasts take a fraction of the time to produce. For once, AI can be synonymous with power efficiency. We'll take it.

👉🏻 Main 🌟 Meta 🌟 Blips 🌟 Blog 👀

I wish you a great week! ✌️ 🇺🇦 🇨🇦 🇪🇺 💪🏻

👤 Personal

#blogging

1️⃣ I'm taking a one-week vacation and will be right back in mid-November. This is why this edition is a little bit early (Friday instead of Sunday). 2️⃣ A very touching personal story from Manton, the developer behind Micro.blog. I can relate. Planting a tree is such a good idea. I wish I had done the same when my parents passed away, but I don’t have the space to do this at my house. 🌳🏡 3️⃣ An unexpected comment on Mastodon from someone who read an article I shared a while ago about being an open blogger.

🗺️ Discoveries

#chatgpt #appleshortcuts

1️⃣ I discovered that ChatGPT can help me have a better understanding of Apple Shortcuts. I’ve been writing shortcuts for a while, but my success has been relatively low. The writing experience is bad and getting the intended results is a challenge. I recently shared that writing and debugging shortcuts can be a frustrating experience. Thanks to ChatGPT’s explanations and examples, I have a much more positive view now. Moreover, ChatGPT can generate a text form of a shortcut. If the app developers diligently created shortcuts support in their app, I can ask ChatGPT to consider apps such as AnyBox and Paste.app, and their respective intents. It's not perfect, but it's a great way to learn building shortcuts.

"Grokipedia is not a 'Wikipedia competitor.' It is a fully robotic regurgitation machine designed to protect the ego of the world’s wealthiest man." — 404 Media

👨🏻‍💻 Writing

#bloggerlife

1️⃣ Over the past month, my writing circled around two big currents: Apple’s evolving (and often exasperating) platform experience—especially on iPad—and a fast-rising reliance on AI-driven tools, led by ChatGPT Atlas. In between, I explored creator tooling, App Store governance, and a few cultural notes. What follows is a concise guide to the month: key themes, notable controversies, the apps and services that surfaced most, and the big takeaways shaping my workflows and outlook.

🌄 Photography

#glass #lightroom

1️⃣ Glass gave a small behind-the-scenes look at the engine, helping them manage the platform. It's interesting, but I wanted to know much more than they were willing to share. A video would have been a good idea. 2️⃣ Adobe launched Lightroom Classic 15, which comes with a bunch of AI-related stuff. Who knew! I'm no longer using Adobe products for processing my photos, but I wanted to pass that information along, just in case you depend on it! This video has all the details. 3️⃣ Meanwhile, we are still waiting for Apple to provide meaningful updates to Photmator and Pixelmator Pro. 4️⃣ On Unsplash, bookmarks are now replacing likes. They made an announcement about it. Speaking of Unsplash, here's a great picture from Zetong. I wonder how much post-processing was involved in that one. 👀

🍎 Apple & Tech

#appstore #apple #appletv

1️⃣ If you plan to get a new pair of Apple AirPods Pro 3 and are a frequent flyer, consider reading this blog post from BasicAppleGuy, who experienced weird noises during a flight while wearing a pair of the shiny new devices. 2️⃣ Apple made a lot of money in 2025. Apple reported record fourth-quarter 2025 results, with $102.5 billion in revenue driven by strong sales of iPhones and services, achieving double-digit year-over-year growth in earnings. Quite impressive. Jason Snell notes that Apple’s “values” messaging has shifted from human-focused themes, such as education, diversity, and social equity, to industrial priorities, including U.S. manufacturing, recycling, and AI investment—reflecting a move from moral activism to economic and technological nationalism. 3️⃣ Apple is marking the 10th anniversary of the Apple TV HD, Siri Remote, and tvOS launch, which introduced apps, gaming, and a new vision for Apple TV that reshaped the platform but never fully met its ambitious goals. Apple TV, the streaming service, not the hardware device, has a new introductory video that plays at the start of a movie, for example. I like it. It’s more colourful, but the sound seems too subtle to me. 4️⃣ Did you know you can browse the Apple App Store using your favourite browser? Yes, but please note that this is only for browsing, not for downloading the app. When sharing a link to an app with someone, the person clicking on it will likely see the web version rather than being directed to the App Store. Have a look for yourself here. Apple also offers a web version of Apple Music, in case you didn't know.

🚧 Special projects

#craft #openai #mcp

1️⃣ Since the start of the following Craft beta round, I started testing MCP with Craft via ChatGPT. So far, I find it relatively simple to set up, but much more complex to think about all the implications for my content organization. The beta period should last all of November. I'm guessing things might change a bit and improve. This will allow me to settle on my workflow.

“Less isn’t more. Less is more honest.” — from the Design Lovers YouTube video channel

📱 Apps & Services

#digitalcreation #appleservices

1️⃣ At Canva’s keynote, Ash Hewson unveiled the all-new Affinity — a unified, high-performance design app combining vector, pixel, and layout tools under one roof — and announced that it’s now free forever for everyone, including future updates, with optional Canva AI integration that respects user privacy. I downloaded the app but didn't install it. I'm curious about the photo-processing module, otherwise this is not really for me. 2️⃣ A recent 9to5Mac story highlights how Apple’s Family Sharing can be exploited by abusive ex-partners, as only the account organizer holds full control—leaving custodial parents powerless to move children’s accounts or prevent tracking, with Apple support unable to intervene. The case underscores the need for dual-organizer roles and stronger safeguards in shared digital ecosystems. 3️⃣ I posted an update about my current content creation ecosystem. It was long overdue. People rejoiced. Not really, nobody noticed. You can see the overview diagram below.

📺 YouTube

#weather #apple #design

1️⃣ Flying through the eye of Melissa hurricane. Astonishingly quiet. And frightening. They do that for research and weahter forecasting. 2️⃣ Forest City, a completely abandoned ghost city, near Singapore. Let’s take a ride to this place through this video. 3️⃣ An intriguing and informative video about design and how it might explain many of Apple's design pivots in the last 20 years.

🌟 Miscellaneous

#ai

1️⃣ A valid comment about coding vs software engineering from Matt Birchler. Generative AI is not about software engineering help, just yet. 2️⃣ Are you bored sometimes and find yourself endlessly scrolling your Instagram timeline or TikTok? Here are a few ideas for you to consider instead. I especially like this one: “Scroll through your photo timeline and browse past photos and memories.” 3️⃣ One last thing, if you aren’t able to play videos inside this document (the Craft version), this is a known issue and you must go to the website instead.

🔮 Looking forward

#automation #workflow

1️⃣ In the next few weeks, I want to spend more time explorer Apple Shortcuts. I feel they are a gateway to very powerful and customizable workflows. As Craft is also gaining much-wanted features related to AI (MCP, API), Shortcuts could play an important role here.

👉🏻 Main 🌟 Meta 🌟 Blips 🌟 Blog 👀

I wish you a great week! ✌️ 🇺🇦 🇨🇦 🇪🇺 💪🏻

It has been a while since my last update in March 2025. Here’s a summary of the changes.

• I removed Brief.news because I no longer think it will replace Mailbrew.
• I removed Mailbrew because I no longer depend on it to consume Internet content. I tried to replace it with Inoreader email digests, but it didn’t work as I wrote here.
• I decided to add ChatGPT Atlas because I now have a solid use case for it: articles summarization and analysis, as I explained in this YouTube video. This means Perplexity didn’t stay from my previous update. I’m focusing and want to settle on OpenAI for the foreseeable future.
• My new personal landing page, which is mostly complete, has replaced the one previously hosted on Craft public documents.
• I also made several visual tweaks to make it cleaner and more visually appealing.

The pace of updates slowed considerably in the last two years. It’s a good thing, and it means I can focus more on content and less on tooling.

Spooky night... ha ha ha haaaaah

👤 Personal

#foodforthoughts
1️⃣ Fall has settled in for good now. It’s my favorite season—summer trails just behind—but autumn carries a particular weight for me. The air thins and sharpens, and with it comes that familiar blend of melancholy and nostalgia. The colors are louder even as the days grow quieter; leaves flare into brief brilliance before letting go, and I can’t help but read a lesson in that. I’ve felt this way for as long as I can remember: a gentle ache for what’s passing, paired with gratitude for the beauty of the in‑between. 2️⃣ Autumn is a hinge, a clean, deliberate turning toward colder, whiter days. The rituals arrive—warmer layers by the door, earlier sunsets at the window, steam rising from a mug. Each small change is a marker in the slow migration from abundance to rest. Maybe that’s why I’m drawn to this season: I like transitions. They make time visible. They invite reflection without demanding conclusions. In fall, I feel both the closing of one chapter and the quiet drafting of the next, and I’m content to linger in that corridor where everything is briefly both.

🗺️ Discoveries

#ai #design
1️⃣ Do you know Charles Addams? He was a popular cartoonist. I love his drawing style and tried to replicate it using ChatGPT. It came out pretty beautifully. In recent months, I found a few drawing styles that I really like. Another example is the one you can find on the "The Ephemeral Scrapbook — Edition 2025-36”. I created a document where I gathered the ChatGPT prompts and samples of these so I can reproduce them easily. 2️⃣ Here's a blog post from Microsoft explaining the evolution of the Microsoft 365 iconography redesign. I like this kind of blog post, but Microsoft trying to convey their motivation around AI and Copilot seems like a stretch. Generally speaking, I see the new icon versions as an improved version. I cannot say the same about Apple's recent icon version centered around Liquid Glass.

“If the strengths of A.I. are to truly be harnessed, the tech industry should stop focusing so heavily on these one-size-fits-all tools, and instead concentrate on narrow, specialized A.I. tools engineered for particular problems. (...). Humanity would be better served by labs devoting more resources on building specialized tools for science, medicine, technology and education.” — Gary Marcus in Is AGI the right goal for AI?

👨🏻‍💻 Writing

#journaling
1️⃣ Most of my writing these days goes into building this newsletter and posting on my blog. 2️⃣ Recently, I started writing in Craft Daily notes. I always like to document what I'm doing. I do this at work all the time in Microsoft OneNote. Every day, I create a new note in a dedicated notebook and write a one-liner about the completed task. Now, I do this at home do document what I'm doing with a computer. It's fun.

🌄 Photography

#source/reddit #nikon #iphone17
1️⃣ We can find great photographers on Reddit, like /unlicensedliensed. Who knew? 2️⃣ Is it worth upgrading to the iPhone 17 Pro? A great article tries to answer a very common question. Coming from an iPhone 15 Pro Max, I would say, no, not at the cost Apple charges for that. Waiting until 2026 to upgrade. 3️⃣ In this video, the author compares the iPhone 17 Pro to the 16 Pro and the Canon R5. You will be surprised by his observations. 4️⃣ Rumors about the next year’s iPhone 18 are ramping up. Next year, we could see the most significant change to iPhone cameras in a long time. 5️⃣ Nikon is about to add a grain effect to my Nikon Zf camera via a firmware update! Cool, but no date given! 6️⃣ It's still too early to tell if the iPhone Air will succeed for Apple. Nonetheless, Tyler Stalman is looking at it from a photographer's perspective. He shares a few details about the iPhone Air‘s photography capabilities that make it stand out from the rest of the iPhone 17 lineup.

🍎 Apple & Tech

#applesilicon #ai #apple #tech #ipad #macos
1️⃣ M5 → M5 iPad Pro → 14” MacBook Pro. 2️⃣ Apple has experienced a series of significant exits from its AI division, which poses a challenge to its ability to compete in the rapidly evolving AI landscape. The departure of Ke Yang, who was recently appointed to lead a team focused on enhancing Siri's capabilities, underscores this issue. 3️⃣ An astute observation from Matt Bircher about Apple marketing photo of the M5 iPad Pro. Apple presents the new M5 iPad Pro like a real laptop, while they present the new M5 MacBook Pro like a computer running a single app. 4️⃣ The new M5 iPad Pro is a bigger upgrade than it seems. Thanks to MacRumors for this upgrade highlight. 5️⃣ This AWS downtime is a reminder how dependent other service providers are. When AWS goes down, even if it's only an AWS region, many things falls apart (the list of web services that were impacted is too long to post here). 6️⃣ I know this company, Quilicot, they have a store less than 2 km from my home, in Montreal, Canada. They made it to the Apple Small Business mini website. I did notice the use of Macs in their boutique. I thought it was a great design fit with the type and brand of bikes they sell. 7️⃣ Finding the next Apple CEO won’t be an easy task if you ask Parker Ortolani. While I agree that finding a new CEO for Apple is not a small endeavour, I don't agree with him on all requirements, especially #2.

🚧 Special projects

#workflow #reading
1️⃣ I spent quite some time recently putting together a solid and durable article reading workflow based on Craft & ChatGPT. I'm really satisfied with it so far, and I'll probably create a YouTube video about this. The workflow also applies to watching YouTube videos, for which I want to summarize and extract as much information as possible. 2️⃣ Also, I finally found a way to use Craft Daily notes as shown in this short video demonstration.

📱 Apps & Services

#app/cleanshot #app/raycast #service/fastmail
1️⃣ CleanShot Cloud and CleanShot X now support user comments on shared screenshots. Judge for yourself in this screenshot example. 2️⃣ Raycast continues its expansion on the iPhone with the introduction of an iOS keyboard. Raycast's iOS keyboard update streamlines workflows. Explore tabs for recents, AI, dictation, quick links, and snippets. See all the details here. 3️⃣ Fastmail now offers a Mac app. Well, it's one of those web wrappers based on the Electron framework. It's not great. It even feels slower than the web version! The positive thing about having this app, though, is getting native notifications and the offline mode. Please make no mistake, I'm still a satisfied user of this service.

📺 YouTube

#service/youtube
1️⃣ I've just noticed that YouTube appears to offer an "Ask" button for each video, as shown in this screenshot. I tried it twice and found the summary quite clear and helpful. The consequence is profound: I didn't watch the videos. As someone who creates videos, I'm pondering the implications for me and all other video creators. 2️⃣ Growing a small tree can be cool and relaxing. Watch it here. 3️⃣ Can we become friends with spiders? Maybe.

🌟 Miscellaneous

#openai #ai #sora
1️⃣ I finally got into Sora and tried it to create cameos with a few prompts. My first cameo was impressive, but the following ones weren’t. I'm not sure that I want to waste too much time (and energy) on this thing. 2️⃣ The header image of this newsletter edition with an Apple logo was taken from another website that writes about Apple and uses a lot of AI-generated artwork. I didn’t ask his permission. Typically, if it were something he created himself, I would have asked for permission to use it.

🔮 Looking forward

#openai #aibrowser
1️⃣ OpenAI released the ChatGPT Atlas browser. It's yet another Chromium-based browser with “some AI” stuff glued on top of it. It is joining Comet and Dia. It's becoming a crowded space. Strangely enough, Google is relatively slow at adding AI to its Chrome browser, I mean, in an obvious and readily accessible way. Nonetheless, I shared a few thoughts about my first hours using Atlas. As someone who tried both Comet and Dia, neither of them clicked with me; Atlas is another story—looking forward to seeing how it will influence my workflows. 2️⃣ As reported by Marcus Mendes from 9to5Mac, Apple is developing a new framework in iOS 26.1 that enables third-party photo apps to perform seamless background uploads of images, enhancing reliability and user experience. This could be a game-changer for secure and reliable photo library backups on your Apple devices. I don't do those but provided with an fully supported mechanism, I would do it!

“Technologies like LLMs have utility, but the absurd way they've been over-hyped, the fact they're being forced on everyone, and the insistence on ignoring the many valid critiques about them make it very difficult to focus on legitimate uses where they might add value.” — Anil Dash in The Majority AI View

👉🏻 Main 🌟 Meta 🌟 Blips 🌟 Blog 👀

I wish you a great week! ✌️ 🇺🇦 🇨🇦 🇪🇺 💪🏻

UFO - Take 2. It's a matter of perspective.

UFO.

As a Craft power user, I still need Ulysses to complete my writing and publishing workflow. I made a video about this.

Oldies.

This week, I decided to add Screen Studio to my YouTube recording workflow. Screen Studio brings simplicity for recording more dynamic screen sequences. Everything Screen Studio does can be done in ScreenFlow, but it requires significantly more manual work. But Screen Studio has a severe limitation: we cannot merge recorded sequences. That’s why I’m keeping ScreenFlow.

In summary, my workflow proceeds as follows: individual sequences are recorded in Screen Studio, exported as .mp4 files, and then imported into ScreenFlow to be assembled into a complete video sequence, which includes the intro and outro sequences with background music. Chapter markers are also added in ScreenFlow before final export. Finally, video subtitles are created using Whisper Transcription and exported as an .srt file, which is compatible with YouTube Studio.

Overall, I do spend more time on video rendering, but I think it’s worth it. Lastly, disk space consumption is way higher than before, with 2x-3x more space consumed than with ScreenFlow alone. Ouch.

One more thing: Screen Studio is the only app that makes the M4 Mac mini fan run at full speed. I wonder if Screen Studio uses Apple Metal technology?

I’ve long wanted to write an article like this one. However, as Apple continued to add to its list of failures, poor Apple, I kept pushing back the deadline. This summer, however, the timing was right. Here’s what I did differently this time.

A few months ago, I started gathering a list of Apple’s failures in a Craft document. I wanted to cover the period from when Tim Cook took over as Apple’s leader, following Steve Jobs’ passing, up until now. For each failure, I wrote a summary that included a description, some context, and a list of potential collateral damage to Apple’s reputation and brand. Then, I turned to ChatGPT for help.

I set up a space to upload files, one for each failure, and began a separate “conversation” to explore areas I hadn’t already covered. This process took a few weeks. I’d revisit one of the failures every other day and continue the conversation until I was satisfied.

Next, I started creating a first draft based on all the conversations in this ChatGPT writing project. It took many prompts to refine the base content before exporting it as a Markdown file. Then, I set up a new conversation, uploaded the file, and asked ChatGPT to continue working on the article, this time in canvas mode. It took many more iterations and manual edits to finish around 85% of the writing process.

After that, I imported the text back into Craft and kept adding relevant facts and comments. As I went along, I started searching for photos that could illustrate each section. I used Kagi Search for all my image searches. For each photo, I wrote a brief caption that gave a unique perspective on the failure it was highlighting.

It’s also worth noting the role of Grammarly. As I finished writing in Craft, I used Grammarly to rephrase parts I didn’t quite like. I ended up keeping around half of Grammarly’s suggested rephrases.

In summary, generative AI was a significant contributor to my writing, either through the use of ChatGPT or with Grammarly’s constant supervision. I’m not sure how I should feel about this, nor how you should think about it, now that you know. Make no mistake, the original writing project idea is mine. The selection of Apple’s failures is mine. The starting point of research is mine. The selection of images is mine. Supervision of ChatGPT’s contribution is mine. But is the final product mine? Anyway, complete transparency, now you know.

Too beautiful, it breaks glass.

Last of a trilogy. See previous two posts.

A more focused street photography example (see previous post). #blackandwhite #blackandwhitephotography #streetphotography

I'm not really good at street photography... am I?

I have always been torn between creating text-only quotes and image-based quotes. Text-only quotes are easier to resurface and index, while image-based quotes are more visually appealing. You’re preference?

I made a little update to my reading workflow, especially the part for newsletter. Look in the table on this page and sort by date to locate the most recent update.

While searching for blog posts on numericcitizen.me, I discovered a few duplicates and some that were no longer relevant. I removed the duplicates, likely caused by previous migration processes, and decided to unpublish the outdated posts. There seems to be a debate about whether we should delete past publications. Some argue that all blog posts, regardless of relevance, reflect our identity and showcase what we once considered important. Others believe that removing irrelevant posts, which they refer to as noise, helps the remaining content stand out. As I agree to both arguments, I’m allowing myself to do some cleanup, from time to time, and it’s ok.

Important additions to my generative AI usage rules: use more than one service, try paid version to get better results, prioritize cloud-based services. More details here.

When I read about vibe coding to quickly create app mockups or even shipping an app to the App Store, I wonder if I could use genAI to vibe code a theme plugin for Micro.blog. That would allow me to use a unique visual theme inspired by my visual branding.

The Who Is Numeric Citizen? website has moved from Cloudflare’s Workers app to Chillidog Hosting. This change was necessary to support PHP, which is required for Elements CMS. Additionally, the publishing workflow is now more straightforward since I no longer need to use a GitHub repository, which was necessary for hosting a static website on Cloudflare. It is rare to simplify a workflow while adding more features, in this case, PHP to implement a CMS component on the News page.

The migration process was relatively simple, thanks to Chillidog support, which was fantastic BTW. The process involved republishing my website using a new configuration publishing setup, which pointed to Chillidog. The setup was straightforward because Chillidog is familiar with Elements, which allows you to download a configuration settings file directly into Elements for setting up the FTP connection. Once republished, I made a DNS change at CloudFlare to replace a CNAME record with an A record to one of Chillidog’s servers. After 15 minutes, it was a done deal.

I’m getting ready to use the upcoming Elements CMS feature when it becomes stable enough for production use. Today, I pushed out a big update to “Who Is Numeric Citizen?” website where I decided to split the Highlights section into four as I’m expecting them to grow over time. As for the CMS feature, it will require a change of my hosting solution. The website is currently hosted on Cloudflare as a worker-based app. I’ll first move the content to Chillidog hosting first, then I’ll start adding the CMS feature in those areas: site news, redo the best articles section and add a tech wish list as CMS entries.

My main website, numericcitizen.me, is now officially using Ghost 6 which was released today. It was a short and painless process to upgrade. While Ghost.org will grandfather current plans, I discovered a price increase for my subscription tier (Creator), going from $25/month to $29/month. It seems that under my current plan, I can get all the juiced up analytics, which is nice. Yet, Ghost.org is a pricey service for a blogger like me.

Because I’m getting email inquiries many times a week for SEO improvement offers, link insertion, ads, etc. I decided to create my official response for these sketchy offers. I hope they understand the message, provided that they read it, of course, which I highly doubt. It’s probably a lost cause.

Because Diagrams for Mac seems to fall in the category of abandonware, if the latest blog post date is any indication, I decided to drop if from my tool set. The app wasn’t updated since macOS Monterey in 2022. Too bad, it was a rather promising diagramming tool.

I’m trying out the new generative AI-based analytics from Tinylytics, and I’m very impressed. Here’s an example for my main website. To my knowledge, that’s a first for website analytics and I hope that Plausible will take a look at this because it’s really useful. Plus, Tinylytics allows you to create your own prompt and see a different take than the one generated by default.

I’ve been quiet lately because I’ve been dedicating more time to learning Realmac Software Elements. I plan to create a few websites for fun. The first will be a new landing page to replace the current one shared with Craft Docs (look here). The second will be my professional website, which I’ll use when I transition to a freelance career. Ironically, the third will be a rework of my current employer’s corporate website, which I find quite unattractive.

So far, it’s a rather exciting journey. Elements is an excellent Mac app, and the team behind it offers a stellar presence on their support forums. This adds to the excitement of being part of a small club trying to build a new app. Elements is still in beta and should launch this year. You should see this video on YouTube showing the app’s user interface.

My experience with Elements reminds me of Apple’s iWeb website editor, which was part of the initial MobileMe rollout. However, Elements is much more powerful and geared toward a different crowd. The learning curve is much steeper, but it is reasonable for a guy like me. Elements is built around Tailwind CSS. I don’t know CSS or Tailwind CSS, but Elements hides its complexity.

Tailwind CSS is a utility-first CSS framework created by Adam Wathan and the team at Tailwind Labs in 2017. Designed to streamline web development, it provides a comprehensive set of low-level utility classes that allow developers to style elements directly in their HTML without writing custom CSS. This approach enables rapid prototyping and highly customizable designs, making Tailwind CSS a popular choice for developers seeking efficiency and flexibility in building modern web interfaces.

As soon as my first project matures enough, I’ll share more about it.

I finally completed the replication of content from the Craft-hosted website to Micro.blog-hosted website. I initiated this migration to reduce my dependency on Craft to host such content. Numeric Citizen I/O still points to Craft-hosted website (https://world.numericcitizen.io/meta), but 95% of the content is now available on Micro.blog via meta.numericcitizen.me.

Am I leaving Craft behind, not anytime soon, but I’m certainly continuing to consolidate my online presence under more open platforms.