Apple's shiny new (and open source!) Foundation Models Utilities package is full of gems. This seems like a great way to prove API before baking it into the OS – I love the compacting code! https://t.co/XfxLXHeNFm
I have been experimenting with SwiftUI realtime object classification, detection, and segmentation using Core AI models. Everything is running locally on iPhone.👇
- Classify: Live image classification with a user‑chosen vision model, PVT v2 (ImageNet‑1k) or CLIP (zero‑shot).
- Detect: Object detection + prediction with bounding boxes using RF‑DETR.
- Segment: Instance & semantic segmentation by text prompt with SAM 3 .
- Ask: Natural‑language Q&A about the scene (text or voice) with Foundation Models + SpeechAnalyzer.
I’m a heavy sleeper.
I’m also too lazy to work out.
So I built Risen — an alarm app that won’t stop ringing until I do push-ups.
Turns out the best way to wake up is to leave yourself no choice. 💪⏰
#buildinpublic#indiehackers#iosdev
@Altawesomeee haha same here 😅
My first app: refreshing App Store Connect like a maniac for days
now: blink and it’s approved
Apple review really said: we got you today 😂
I’ve been shipping iOS apps since 2019.
10+ apps shipped.
100k+ downloads.
$2k/month in revenue.
Some flopped.
Some are growing.
Now building:
→ Tempus — ADHD Planner with AI
→ Noota — AI Note Taker & Transcription
→ Mona — Budget & Expense Tracker
→ Visty — Business Card Scanner
Goal: $5k/month by the end of the year.
I share real numbers:
revenue, failures, experiments.
Follow along if you're building too.