We're vibing this nice Sunday morning. Added more functionality. Using the approx 3500kcal ~= 1lb of fat, we now show a really cool animated ring that fills up to 3500 in either +/- direction, and completing the circle adds it on the bottom. So e.g. 3 green circles =... 3lb lighter, in theory :). 3 conversations were used: Refactor the AppStorage to be better / cleaner and shuffle elements around a bit Clamp the display to always be in range [-3500, 3500], which is 1lb of fat, and show lb of fat as circles on bottom Making the calorie counter have a nice ring that fills upshow more

I just vibe coded a whole iOS app in Swift (without having programmed in Swift before, though I learned some in the process) and now ~1 hour later it's actually running on my physical phone. It was so ez... I had my hand held through the entire process. Very cool.

I didn't even read any docs at all, I just opened a ChatGPT convo and followed instructions.

A number of people asked If I can share the convo and yes sure - these were the 4 convos with my super noob swift questions lol: 1 starting the app 2 enhancements 3 adding AppStorage to persist state over time 4 deploy to phone and this is what it looks like late last night I'm already happily using it today for tracking, and will probably hack on it more on this fine sunday.

Sweet, list it on Apple Store!

This is the Keg It™ Keg Kit we created after being frustrated that there wasn't a midsize option that would allow us to bring and serve drinks on tap. Now, you can take and pour the perfect cocktail, seltzer, beer, cider, cold brew coffee (the list goes on) like a pro!

You were threatening the model, lol. It seems that the same model was able to pull it off anyway— just by you being more precise, giving it examples, and specifying the kind of results you expected.

It doesn't show... What model did you use? o1-pro, o3-mini-high? 4o?

While interesting…caloric burn is data is a joke. Wearables tend to overestimate. In addition the body adapts to loads becoming more efficient. So crap data = crap output albeit in a cool display

Instead of pushing buttons, just upload images. It does pretty good job in guessing calories

Who's 'we' ?

Oh this looks nice! Congrats!

Smart visualization approach! Would love to extend this concept to AI agent task monitoring - imagine tracking completion stages with a similar ring pattern in the agent DevUI.

wow. very nice vibe coded app. you should consider integrating an llm. if you don’t know what that is, here’s a good primer.

It works even better with flutter and android studio. Just initialise the sample flutter project and open the android emulator. Then ask the cursor or windsurf to build what you need and refresh the emulator. You can almost build the entire app "live"