I’m a solo developer, and I recently gave myself a 20-day challenge: learn iOS development from scratch and ship something meaningful.
The result is MelloPal — a minimal iOS app that offer gentle reflections and habit nudges based on your meals. It's meant to feel like a soft, kind companion instead of a rigid diet tracker.
Why I made it:
Most nutrition apps made me feel worse: judged, overwhelmed, or pressured. I wanted something that focused on encouragement and emotional support rather than optimization.
What I used:
- GPT for Chat
- Claude code
- Cursor as my dev environment
What surprised me:
- App Store edge cases take up more time than expected
- It’s easy to under-scope early, but still overbuild by accident
I’d love feedback on:
- Whether the concept resonates with you
- Things I should consider improving or removing
- Tradeoffs you’ve faced on your own solo dev journeys
Thanks for reading — happy to answer any questions or ideas.
Awesome! It looks like you’re building a “reasoning tree” approach with runtime-level context engineering and pruning.
Quick question — how does the context-pruning mechanism decide which KV states to discard vs. retain? Just trying to understand how it balances memory efficiency with reasoning depth.
I’ll sign up and try out the API — excited to try it out!
Really cool work! I saw the “Selective Working Memory” section, are there hooks to swap in a custom retrieval store or memory layer, or is that all internal to TIM?
We’ve developed an algorithm called L-Mul to tackle AI’s growing energy consumption problem. Large AI models, like those behind ChatGPT, consume enormous amounts of electricity daily. L-Mul reduces energy use by up to 95% by replacing energy-intensive multiplication operations with simpler addition operations, without compromising performance. We’re excited to share this approach with the community, as it could make AI development more sustainable and cost-effective.
I’m a solo developer, and I recently gave myself a 20-day challenge: learn iOS development from scratch and ship something meaningful.
The result is MelloPal — a minimal iOS app that offer gentle reflections and habit nudges based on your meals. It's meant to feel like a soft, kind companion instead of a rigid diet tracker.
Why I made it: Most nutrition apps made me feel worse: judged, overwhelmed, or pressured. I wanted something that focused on encouragement and emotional support rather than optimization.
What I used: - GPT for Chat - Claude code - Cursor as my dev environment
What surprised me: - App Store edge cases take up more time than expected - It’s easy to under-scope early, but still overbuild by accident
Here’s the app (iPhone only): https://apps.apple.com/app/id6748720668
I’d love feedback on: - Whether the concept resonates with you - Things I should consider improving or removing - Tradeoffs you’ve faced on your own solo dev journeys
Thanks for reading — happy to answer any questions or ideas.