Numeric Citizen Blog

A quote from John Ternus’ internal memo leaked today (emphasis is mine):

As you’ve by now heard, Tim has announced that he will be transitioning into the executive chairman role, and in September, I will become Apple’s new CEO. It has been such a privilege to lead the hardware engineering team, to be part of such remarkable work, and to see all of you in action, determined as ever to do everything we can for our users. I look forward to working with you very closely in my new role. Needless to say, I still plan to be very hands-on.

I like this a lot. I always admired people who can be very high-level and very hands-on while being relevant at both levels.

John Appleseed:

Ternus’s other task will be to repair an incredibly fragile relationship with developers, who have been vocal about their dissatisfaction with Cupertino.

Priority #1 or #2. If #2, then the software story has to be #1.

The latest Huawei folding phone kind of previews the iPhone Ultra — 9to5Mac

Apple is believed to be going for a wider screen on the outside of its foldable iPhone, which creates a wider aspect ratio for the larger screen on the inside.

I wasn’t very keen to such devices until I saw and okayed with one recently. I’m not sure about this form factor, though. It reminds me of the fat iPod nano. What’s I’d like to see in the future is a foldable iPad where the full size would be equivalent to the current 11-inch iPad, but once folded would be closer to a mix of the iPhone 17 Pro Max and an iPad mini.

App host Vercel says it was hacked and customer data stolen — TechCrunch

Vercel said the hack may affect “hundreds of users across many organizations,” and not just its own system, warning of potential downstream breaches spanning the tech industry.

All my web apps are hosted on Vercel. I got an email this morning to tell me my account wasn’t impacted by the data leak. Should I trust this statement? One thing that blows my mind: how on earth such a serious company don’t have a more restrictive policy as to what employees can download and test?

Now that my Mailbrew account is closed, I have moved many of my Brews¹ to my RSS Flow web app. This is my home page with many photo-heavy sources. Pretty nice, enh!

I’ll never buy anything other than traditional house furniture at IKEA. Don’t trust anything involving electronics or smart home appliances. I learned the hard way. 🤬

After several years of loyal service, I finally closed my Mailbrew account. This service was sold by its creators a few years ago, and since then, development had completely stopped. It’s a shame because when Mailbrew first appeared, it was an innovative idea that filled a niche for news and reading enthusiasts. I’ve moved on to something else. My reading workflow evolved around RSS and using the best client for the task.

Just finished watching this video from Tom’s Guide with Apple’s Joz and John Ternus. I paid attention to Ternus’s words and answers while asking myself: is this guy really the CEO Apple should be transitioning to? I think so. I much prefer his tone and more apparent enthusiasm compared to Tim’s.

For this fall’s iPhone and iOS 27 releases, I hope Apple will include new wallpapers from the Artemis II mission.

I believe I decided to build my web apps at the right time¹, because if I did it now, it would take two or three times longer due to the current credits consumption rate enforced by Anthropic. I made a little tweak to my dashboard web app this morning, and I’m already at 36% for the current session. It’s really that bad. I wouldn’t pay 200$ a month to get more credits.

Apparently, the iPhone 18 Pro will offer two possible shades besides deep red. I might go with the gray version this time! Or the darker one.

This morning, I realized that managing open issues and bugs on GitHub is advantageous: the more detailed each open issue is, the more effective it serves as a prompt when importing into Claude Code to initiate a new bug-fixing session. Claude Code can also close the issue at my request and link it to a specific GitHub commit.

I’ve been testing the latest release of the Claude Desktop app, and I must say, more than ever, I prefer integration to splitting features across many different apps. I’m also leaving the CLI behind for now.

Gemini App for Mac:

Gus Mueller:

Took a peak at it and … it contains 1,856 Objective-C classes whose class name starts with Java. What in the world are they doing? So I had Gemini analyze Gemini. Looks like there’s a lot of shared Android code in there, but compiled to Objective-C and Swift.

Better consider that 95% of new apps these days aren’t native to the platform.

For all my pending issues across my different Claude Code and web apps, I just realized I could (and probably should) use GitHub for issue tracking instead of Craft. Additionally, I could develop a web app to monitor and manage all open issues across my repositories!

This morning, I used Claude Code to replicate the visual style of my blog site to one of the first web apps I created using Claude, a Micro.blog front-end for writing and posting a single post. The end result is spot on.

Chris Espinosa from Apple sharing a job offer:

We’re hiring in the tvOS Engineering group at Apple. Real programmers to really write real code.

https://jobs.apple.com/en-us/details/200602666-0836/ios-engineer-apple-tv?team=SFTWR

“Real programmers to really write real code.” 🤔 This sounds a little bit off.

Today, I tested Ollama and Locally AI more extensively on my M2 MacBook Air, and it was quite demanding. It’s no surprise that a serious local AI setup requires an Apple M5 Pro or M5 Pro Max with at least 16 or 24 GB of RAM. My M4 Pro Mac mini has 24 GB, and I could use it remotely through an SSH session. This experimentation puts any plans to replace my aging M2 MacBook Air into perspective.

Anthropic Rebuilds Claude Code Desktop App Around Parallel Sessions:

Anthropic has released a redesigned Claude Code experience for its Claude desktop app, bringing in a new sidebar for managing multiple sessions, a drag-and-drop layout for arranging the workspace, and more.

I’ve been testing the new fat client and found it to be familiar yet overwhelming. It’s taking the shape of a full IDE. Monolithic clients aren’t getting the favor of people apparently but I prefer this approach over separate apps.

Creating an email summarizer was simpler than expected. However, Claude AI struggled significantly with email decoding and data extraction. While one might assume these processes are well-documented and easy, that doesn’t seem to be the case. Additionally, setting up a new Gmail account proved to be unreliable. I encountered numerous errors at various stages, making me question whether the process actually succeeded. You’d expect Google to handle this smoothly, but unfortunately, I wasn’t so lucky.

Here’s the overall workflow.

Microsoft Raises Prices for All Surface PCs, Making Them More Expensive Than Equivalent Macs — MacRumors

Microsoft’s PCs are now more expensive than their Mac equivalents, which is good news for Apple.

How long can Apple hold any price increase?

On the Name of Apple’s Foldable iPhone — Daring Fireball

I have no inside knowledge about what Apple plans to name this device, but I’ll eat my proverbial hat if they name it “iPhone Fold”. That name is so dumb it’s what Samsung calls their foldables. You don’t name a device for what it does, you name it for what it connotes.

The iPhone Duo potential name is not doing it either because it denotes a device with two screens or two sides that you fold together.

With my blog’s new custom design in place, I’m considering my next project: developing an email summarizer using Gmail, n8n workflows, Claude AI, and Discord. I don’t plan to use this often, but I do have some emails that I get that I wish could be summarized just by sending them to a dedicated email address.

Inoreader announced support for third-party AI providers for articles summarization. Anthropic and OpenAI are supported among others. Just enter your own API key and voilà! But there is a big catch: even if available for Pro plans, you need an add-on upgrade to enable this! That, I don’t understand because in this scenario, Inoreader is in fact delegating the LLM so they incur not additional costs. I find this perplexing to say the least. Or I might be missing something. I hope someone at Inoreader will catch this comment.

Hacker News’s article “Ransomware Is Growing Three Times Faster Than the Spending Meant to Stop It”:

Ransomware leak-site claims surged 30.7% year-over-year in 2025 to reach 7,760 incidents, significantly outpacing the 10.1% growth in worldwide security spending ($213 billion), indicating a widening gap between observable threat volume and security investment.

The article doesn’t say what is causing this surge, and if AI has anything to do with it. I would bet that AI might be helping hacker groups.