@thtRajasthaniGuy

The "Local First" Approach: Testing AI with Ollama Before Going Mobile

Apr 17 · 2 min read · I’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 loca

Beyond the Chatbox: Structured Data and the Art of Prompt Compression

Apr 8 · 2 min read · I’ve spent the last few posts learning how to talk to an AI. Now, I’m learning how to make the AI talk back in a way my code understands. If I want to build a weather app, I don't want a poem about ra

Prompt Engineering 101: How to Give Your Mobile AI a Memory (and a Brain)

Apr 7 · 2 min read · I used to think that "Chatting" with an AI was like a real conversation. But as a developer, I’ve realized it’s more like a movie script that we keep rewriting and resending every time the user types

GGUF, Quantization, and Pruning: The Three Keys to "Shrinking" an AI Brain

Apr 5 · 2 min read · I used to think that "smaller model" just meant "worse model." But today I learned that there are two separate ways to make an AI fit on a phone: you can make its memory less precise (Quantization), o

Temperature, System Prompts, and Why AI Has No Memory: The "Personality" of LLMs

Apr 2 · 2 min read · Context I used to think LLMs were like databases—you ask a question, you get the stored answer. But after playing with Temperature and System Prompts, I realized they are more like improv actors. They