/rant on
Can you believe it? I updated my M4 iPad Pro today to beta 2 of iPadOS 26.3, thinking I would see some much-needed fixes, but elas many visual bugs are still unfixed, bugs that were there in 26.1 or even 26.0. I mean, bugs that are very easy to catch and experience. I can’t believe I’m the only one experiencing those. One example: when sliding up an app to return to the home page, the background briefly disappears.
Please, Apple, stop piling up new features and fix your shit.
/rant off
After reading a recent Gruber article about the macOS Tahoe window-resizing issue, I found a setting in Appearance that keeps scrollbars always visible. It’s somewhat odd because of the scrollbar’s thickness. I wish Apple would make them thinner and less noticeable. I’m unsure if I’ll get used to this.
Note: On Windows 11, scrollbars are always visible by default but are less obtrusive. 🤷🏻♂️ Apple was once known for leading with excellent design and great visual taste, but this is less obvious nowadays.
Back in November, Google announced Private AI Compute, positioning themselves to offer something like Apple’s Private Cloud Compute. It might be something that OpenAI wasn’t willing to do or didn’t see a fit in their business mission. By offering Private AI Compute, Google might have secured the business with Apple. Anyway, it’s becoming impressive how Google is taking back the lead in AI. Lastly, maybe we will see Google Gemini being added to this week’s next beta of iOS 26.3 to go side-by-side with ChatGPT?
I just discovered that Raindrop.io offers many integrations, including n8n! I might need to reconsider my bookmarking strategies, yet again. I’m currently using Anybox. 🤔 I’m exploring ways to move the data around. If you made a similar move, I’ll be more than happy to learn about your experience. For now, I’ll prompt ChatGPT for strategies.
Inspired by basicappleguy on Mastodon, here’s my rating of each Apple product. Design, usefulness, feature focus, maturity, and usage frequency are the key factors here.
This diagram tries to illustrate the how modern AI, Claude AI in particular, compares to traditional computing paradigm. Models more or less are processors, Agents are more or less the operating system and Applications are more or less Skills. It’s interesting, but I’m wary about agents because they open up too many pandora boxes.
I made two important changes this morning for my automation-related operating environment:
My first bad experience: the code generated by Claude Code made my dashboard unresponsive in my browser. Eventually, the data stopped updating. After a ten-minute debugging session, I asked Claude Code to revert the change, and it did so promptly. But then I started getting execution failure notices on Discord. A lot of notifications. Then I started investigating…
It appears the browser was making frequent refresh requests to one of my workflows, which depleted my Claude pay-per-use credits. Bummber. Looking at my n8n dashboard, I saw that one of my workflows was failing because of that. Logs were confirming the problem with the interaction with Claude AI. As shown on the graphs below, my instance CPU usage went through the roof. Ouch. Now I know what happened, and the problem was fixed. Now, I should find a way to rate-limit this type of behaviour. That’s for tomorrow, I guess. 😅
Ten days into 2026, I have achieved much more than I anticipated. If I maintain this pace, I will complete my list of wild ideas soon. It’s not just about checking items off the list, but also about learning a lot along the way. It’s very fulfilling.
I’m making good progress on my personal dashboard idea. While people may criticize LLMs and enjoy coding for fun, for me, it opens up possibilities I couldn’t have imagined before.
