The "Local First" Approach: Testing AI with Ollama Before Going MobileI’m using Ollama and Google’s latest Gemma 3 model. My goal is simple: Understand the difference between the /api/generate and /api/chat endpoints and learn how to bridge my React Native app to a locaApr 17, 2026·2 min read·2
Temperature, System Prompts, and Why AI Has No Memory: The "Personality" of LLMsApr 2, 2026·2 min read·7
Tokens and Context Windows: Why My App Can't Remember EverythingJourney Context After deciding to go "Local," I realized I couldn't just throw a 50-page PDF at a mobile LLM and expect it to work. I had to go back to the basics of how these models "read." LLMs are Mar 27, 2026·2 min read·13
Learning AI as a Mobile Developer — Why I'm Exploring Local LLMs for Mobile AppsJourney Context After 6.5 years of building react-native apps. Most of my work has been focused on building production apps, integrating APIs, optimizing performance, and shipping features. But insteaMar 25, 2026·3 min read·12
Upgrading React Native: A Pragmatic ApproachWhen we recently upgraded from version 0.74 to 0.81, the journey taught us valuable lessons about taking incremental steps over quick fixes. Here’s our story and the approach that worked. Why the Upgrade Helper Wasn’t Enough We started, like many dev...Nov 15, 2025·6 min read·4
The God Hook Anti-pattern: When One Custom Hook Does Too MuchI used to think I was writing clean code. I'd extract all my business logic into custom hooks, and move on. Then six months later, I'd come back to that code and think: "What the hell was I doing?" Here's the thing - I was creating one massive hook t...Nov 6, 2025·7 min read·5
Why new Architecture introduced in React NativeIn 2022, React Native dropped version 0.68. That release was a big deal because it introduced something called the “New Architecture.” At first it was optional, but now (as of 0.76) it’s on by default. But why did React Native even need a new archite...Oct 11, 2022·2 min read·77
