All Posts

After spending 6 months using Cursor and 2 months with Claude Code for client work and personal projects, here's what I learned about these AI coding assistants, including the surprising ways they differ and how I think about their value.

How I built an AI-powered engineering team that assembles backend, frontend, and test modules on demand—using local LLMs with Ollama, dynamic templates, and robust Docker sandboxing.

How I built an intelligent chatbot to represent my professional brand on my website using context injection, structured outputs, and an evaluator LLM—all without needing vector databases or RAG.

A hands-on look at fine-tuning open source AI models using LoRA/QLoRA techniques on Amazon product data. I discovered how a fine-tuned 8B parameter model outperformed GPT-4o and Claude, while navigating the practical challenges of limited GPU resources and hyperparameter optimization.

A hands-on look at fine-tuning open source AI models using LoRA/QLoRA techniques on Amazon product data. I discovered how a fine-tuned 8B parameter model outperformed GPT-4o and Claude, while navigating the practical challenges of limited GPU resources and hyperparameter optimization.