Artificial Intelligence
-
From Prompting to Understanding LLMs
Like most developers, my initial experience with LLMs was pretty straightforward. I made API calls, experimented with prompts, tweaked instructions, and tried to get better responses from the model. Most of my focus was on the application side: how to integrate an LLM, structure prompts, and use the responses to build useful features. The model… Continue reading
AI, ai-architecture, ai-engineering, ai-infrastructure, application-development, Artificial Intelligence, ChatGPT, developer-learning, generative-ai, inference-engineering, large language models, llm, LLM, AI, Artificial Intelligence, LLM Inference, Generative AI, Large Language Models, Software Development, Application Development, AI Engineering, Prompt Engineering, Machine Learning, Open-Weight , llm-inference, Machine Learning, open-weight-models, Prompt Engineering, rag, self-hosted-llms, Software Development, technology -
AutoMapper Went Commercial: Your Four Options and How to Migrate
AutoMapper moved to a commercial licence at $4,000/yr. Your four real options, with migration steps for Mapperly, Mapster and hand-written mapping. Continue reading
-
MediatR Went Commercial: Replace It, Pay for It, or Write It Yourself in 50 Lines
MediatR is now $4,000/yr. Pin the MIT version, switch to source-generated Mediator, or write the whole thing yourself in fifty lines — with the code. Continue reading
-
Aspire · Frontend Hosting
Next.js Under Aspire Aspire will happily start your Next.js dev server. Getting the port, the API origin, and the published image right is where the real work is. Component Version Aspire 13.4.6 Next.js 16.3.1 .NET 10 Published August 2026 The pitch for putting a Next.js app under a .NET Aspire AppHost is not that Aspire… Continue reading
-
Unlocking Semantic Search with Vector Embeddings
How Machines Understand Meaning — And How You Can Use It for Smarter Search 1. Introduction: Why Do We Need Embeddings? Traditional search engines rely on keyword matching. If your search query includes the words “best pizza,” it looks for documents with those exact words. But what if a document talks about “top-rated Italian food”… Continue reading
-
Why Prompt Engineering Isn’t a Reliable Skill
Prompt engineering is tweaking inputs to get desired outputs from AI models like ChatGPT. It’s not engineering—it’s trial and error. Why Prompt Engineering Falls Short: 1. No Foundational Principles: Unlike engineering, it lacks structured techniques or frameworks. It’s about guessing, not systematic problem-solving. 2. Unpredictable and Non-Reproducible: A prompt that works today can fail tomorrow.… Continue reading
