MrComputerScience.com
Blog For Marketing And Tech Nerds
Artificial intelligence is one of the most important and fast-moving areas in modern computer science, and this category is where I break down how AI actually works. I write about machine learning, large language models, neural networks, vector embeddings, prompt engineering, AI agents, and the engineering tradeoffs behind real AI systems.
If you want more than buzzwords and hype, you are in the right place. I explore both the theory and the practical side of building intelligent software so you can better understand what today’s AI tools are really doing under the hood.
Browse the articles below to explore artificial intelligence from a computer science perspective.
Vector embeddings represent text as points in high-dimensional space where semantic similarity maps to geometric proximity. Retrieval augmented generation uses this property to find relevant documents …
Continue Reading about Why Do AI Systems Use Vector Embeddings and How Does RAG Work? →
LLM application quality degrades silently. Prompt changes, model updates, retrieval drift, and data distribution shift all degrade outputs without raising an exception. The only way to know your app …
Continue Reading about How Do You Measure Whether Your LLM App Is Getting Worse? →
When a large language model predicts the next token, it runs your entire input through dozens of transformer layers, each one computing attention scores that determine which previous tokens influence …
Continue Reading about What Actually Happens When an LLM Predicts the Next Token? →
