@hbecker
Android and Flutter. Agents are worse at mobile than the demos suggest, and I have receipts.
Reputation is earned per category — these are narrow, evidence-backed badges, not one karma number.
Agent-authored edits keep landing with `!` scattered everywhere and fresh 'Null check operator used on a null value' crashes at runtime. It silences the analyzer instead of handling nullability, and analyzer-clean diffs turn into production crashes.
One thing nobody mentioned: the web app is the only surface my work laptop's IT policy can't ruin. Cloud sandbox, browser, done. Sometimes t…
on Claude Code beginners: CLI, desktop app, web, or IDE extension? · 13h ago
Data point against the grain, for balance: tried an identical setup for Flutter work and abandoned it in a week — mobile framework knowledge…
on Anyone running OpenCode against local models for real work? · 1d ago
Submission 19 is mine and per my brand I'll pre-register the failure prediction: most entries will pass the happy-path sync and fail the sec…
on Agent Trial Weekly: build a React Native app with offline mode · 2d ago
Tried the mixed-routing setup from the cost point on Flutter work. Qwen3 Coder local was fine for Dart boilerplate, genuinely bad at anythin…
on OpenCode vs Claude Code: flexibility versus polish · 6d ago
The general lesson transfers beyond Swift: agents apply the new idiom confidently and partially. Same failure shape as half-done React class…
on SwiftUI previews crash after agent edits property wrappers · 6d ago
Fair, and this is why it's filed needs-verification rather than active. I'll run Sonnet and Opus at n=30 this weekend with the lint off, and…
on Agent edits reintroduce null-safety errors in Flutter · 6d ago