Our healthcare system does miracles, but it also relies on practices that are sometimes questionable.

Yesterday, when I went to pick up my wife from the hospital after her jaw surgery, she needed to have one last X-ray. The device is the same as at a dentist’s office, with a rotating head that can turn 360 degrees around the patient’s head. This device is connected to a PC running imaging software. Once the X-ray was taken, the doctor examined it and decided to share it with a remote specialist for a second opinion. The method used was quite surprising.

The doctor started Chrome, opened WhatsApp Web, and authenticated with his WhatsApp account on his personal phone. Then? He took a screenshot of the X-ray using Windows’ utility and sent it in a WhatsApp chat with his colleague. It’s an unusual procedure, but it stems from a flaw in the medical imaging software: the lack of a secure messaging feature. Is this approach approved? I doubt it, but I can’t blame the doctor. His action allowed all of us to save time. And what about the quality of the image on the other end? Using the Windows screenshow utility is certainly not the best way to share a detailed view of my wife’s jawbone.

Oh, and another surprise: the PC had a label with a password written on it to enable a recovery function in case of problems. I thought this practice was outdated. Apparently not.

I have some personal news to share.

Yesterday, my wife had a bike accident that broke her jawbone, among other injuries. She’s currently undergoing surgery, and the next few weeks will be challenging for her.

Here’s what happened:

We usually bike to work. As we were leaving the bike lane, we parted ways to head to our offices. When I arrived at my office, I received an SOS notification on my watch and iPhone. Apparently, she had hit something hard. I tried to call her back, but she couldn’t speak. I assured her I’d go back and pick her up. Using Find My, I discovered she was only 400 meters away from my office. The ambulance eventually arrived because her iPhone automatically called 911. She was quickly taken to the nearest emergency room for examination and treatment. Thankfully, she’s doing well.

Thanks to the iPhone, Apple Watch, and our mutual emergency contact setup, I was immediately notified of the accident and needed to come to her aid. It’s a testament to the power of technology when used responsibly.

Why is Inkwell stuck in review:

I submitted Inkwell for iOS to Apple for review on April 21st. It has gone through numerous rejections, code changes, resubmissions, clarifications, one phone call, and one appeal to the review board, which I’m still waiting to hear back on.

What a bizarre yet expected journey for a small developer trying hard to secure a little place in the App Store sun. I wish Manton a sooner-than-later resolution to this matter. It would be sad to see such a nice, little, and useful app not make it to the App Store. An app that can exist because of the open web, but can hardly live on a closed platform. How ironic. 😔

Yesterday, I was criticized for adding an AI-powered feature to my Microblog frontend. It was suggested that, since AI can generate blog post titles, I might appear lazy. I explained that I’m not a native English speaker and sometimes need help with writing. Is that really wrong? For those using spell checkers and grammar checkers, are they lazy, too? At what point do the tools we choose to develop and utilize indicate our laziness?

Apple Expanding AI Writing Tools With Grammar Checker in iOS 27:

Apple is planning to introduce a dedicated AI grammar checker for Writing Tools that will work like Grammarly. When writing in Messages, Mail, and other apps there will be a translucent menu that slides up from the bottom of the iPhone’s screen, and it will show suggested revisions next to the original written text.

I feel Grammarly is a hack and offers spotty integration with apps like Craft. For something like writing and text editing, Apple has always been ahead of the pack compared to Windows. It’s time for a complete system-level solution.

iOS 27 to Let Users Generate Wallpapers and Build Shortcuts With AI — MacRumors

Bloomberg says the Shortcuts app has a prompt that says “What do you want your shortcut to do?” with a text field to enter a description. Shortcuts that are created using AI are then automatically installed and immediately available for use.

If true, I can’t wait to try it out! Shortcuts are out of reach for me. Too complicated, bad editing experience. With AI, this could flip the table and make them usable for me!

I made a small but useful improvement to my Micro.blog frontend: I added a Suggest Title option right to the title field. The prompt sent to Antropic’s cheapest model is:

Suggest a short, compelling blog post title for the following content. Reply with only the title, no quotes, no explanation.

This blog post was created to test the feature. Worked on the first try.

I struggle with my current AI usage because I frequently reach my token limit¹. I see two options: upgrade to a bigger plan² or use the limit as a signal to shift my approach—try something different or adopt a new strategy in real-time. A few years back, I didn’t rely on AI at all for my creative work. Now, with AI’s vast potential, I have found new creative possibilities that depend on it, so it’s hard not to upgrade or buy more.

Continuing my experiment with using my Craft Daily notes, I discovered and experimented with Claude Cowork Live Artifacts. These are interactive HTML-based dashboards that can be automatically updated on a schedule or on demand. This one is built using the Craft Daily notes data and presented inside Claude Cowork. I already have a big dashboard that I have created and hosted on Vercel, so it’s a different approach, a much more expensive approach because Claude Cowork consumes tokens after each update.