If you are releasing for every country you might need to do a special form on the App Store for the EU region before they are allowed to distribute your app. I had found this out when I first released mine.

As of the moment, we are only in the U.S but yes you're right on that.

Awesome job! Congrats on the launch!

I like the idea of exploring what others had found before. Maybe it doesn't need to be gear towards just travel but also this gives an opportunity for locals to explore places they've never knew before too?

I've also recently launched a walking app - made for myself but thought others would enjoy too. I had added an anonymous collective walk counter which encourages others to keep walking.

BTW, Mapbox does give sponsorships to projects/apps for displaying how their product is being used so once you get to a certain level you could submit a form for it. I know this project was sponsored by them: https://gpx.studio/

Here is my project if you are interested to checking out. Feel free to take any feature you find in there for your app. https://github.com/walktalkmeditate/pilgrim-ios

Hey man, congrats on the project! And to answer your question, the app is geared towards exploration in your city as well as others. So whether you're planning on going into downtown to explore new places or planning a trip to Tennessee, you're covered both ways! Thanks for the info on the sponsorships, that's my first time hearing about it. The more you know lol.

There is also this project for using email as a coordination layer between agents for multi-agent workflow.

https://github.com/Dicklesworthstone/mcp_agent_mail

I feel like the exponential growth of the models will make this a non-issue in the future. So the tweaks we might make right now might not be even more with when even more powerful models in the future come.

Yes and no. Imagine some super intelligence tackling the unmaintainable mess. It can untangle it, but the problem is that unless you have a test suite that's covering 100% of possible cases (which should on it's own enough to build the codebase), you will stumble upon "what's actually the intent here" problem. Some other software depending on buggy behavior on this one etc.

Which is why I think additional intent preserving abstraction is where software coding agents are likely heading.

exponential what? Marketing aside in day-to-day use models get worse, not better.

I'm working on app for walking based on the practice of walk, talk, meditate.

For now it's just for iOS but currently I'm working on porting to Android.

https://pilgrimapp.org/

This sounds like a monk-styled meditation retreat where one just get fed and can just keep doing meditation all day alone.

Sounds a heaven for someone who is ready for it but hell for those whose thoughts run amok.

You getting one hour of sleep is meditating and no going outside?

There is also another movement to stop Flock. And a discussion [1]

[1] https://news.ycombinator.com/item?id=47772012

I feel like this can be summed into 3 words: Discernment is Key.

I built something recently for myself which is based on the any device philosophy using a Telegram bot approach and like the creator of this app uses a private Github repo as the source of truth.

I use it for just collecting anything I find interesting around the web.

https://github.com/momentmaker/to

Installed it just now. The most surprising line for me was "Conversation $225 / 496 turns". Basically half my turn count this month was chat, not building. Had no idea that ratio was so off.

Cache hit rate is another metric I wouldn't have looked at otherwise. 98.2% on Opus 4.6 here. Apparently that's the difference between a $2k month and something much worse.

Activity classification is the actually useful feature though. Most token trackers just tell you total spend. This tells you what kind of work the spend went to.

Nice work!