It took me the drive, Codex and Claude Code, four days, and voilà! Things 3 is now a thing of the past; I’m using a perfect-for-me custom-built task manager web application running on Vercel/Neon. Things 4 might go subscription-only; I don’t care.

After largely completing the transition from Things.app to a version built with vibe coding on Next.js and hosted on Vercel, I decided to switch from Airtable to a Postgres backend. The free-tier on Airtable only allows 1000 public API calls, which wasn’t sufficient. To avoid hitting this cap constantly, I, with the help of Codex, migrated to a Postgres database called Neon, available through Vercel’s marketplace. I already use Neon for my bookmarking web app, so the change was quite smooth. I didn’t need to move any data since I am still in the late development phase. Now returning to other fine-tuning tasks.

Well, well, well, it seems to be happening much quicker than originally thought. I’m about 70% done with this already! I still like Claude Code more, but Codex is more efficient at testing the UI in its browser than Claude Code. And the in-browser cursor, which is 100% independant than the Mac cursor, is super cool to see in action.

So far so good with OpenAI Codex. I prefer Claude Code’s look and feel, but Codex seems more like something Microsoft would build: plain, without soul. My data model is completed and implemented in AirTable. The basic web UI is running, but is lacking many basic operations like create, update, and delete for tasks, projects, etc. It took me less than two hours to deplete my token allotment. It’s a slower rate than with Claude Code… but still, it’s quickly gone.

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?

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.