Author: Eugene

Azure Data Engineer/Architect

Conditional Trade-Off Graphs – Prolog in the LLM Era – AI 3rd Anniversary Special

Skip Intro. 🎉 Welcome to the AI “Go-to-Market” 3rd Anniversary Special!! 🎉 Starring ... 🌐 The Semantic Web ⚙️ Event Processing 📊 Machine Learning 🌀 Vibe Coding 🦕 Prolog … and your host … 🤖 ChatGPT!!! Following is ChatGPT 5's self-written, unedited, introduction monologue—in a Johnny Carson style. Please do keep reading because this blog … Continue reading Conditional Trade-Off Graphs – Prolog in the LLM Era – AI 3rd Anniversary Special →

Long Live LLMs! The Central Knowledge System of Analogy

Situation Over the past few months there has been a trend to move from referring to "large language models" (LLM) to just "language models". The reason for that is the recognition that small language models (SLM) have clear advantages under certain situations. So "language model" is inclusive of both. And of course, as soon as … Continue reading Long Live LLMs! The Central Knowledge System of Analogy →

Context Engineering and My Two Books

“Context engineering” is emerging as the evolutionary step over prompt engineering. It's the deliberate design of everything an AI system can access before it produces an answer. The goal is to make it work on the right problem, with the right facts, under the right constraints. That is, by mitigating "context drift" as the AI … Continue reading Context Engineering and My Two Books →

Stories are the Transactional Unit of Human-Level Intelligence

The transactional unit of meaningful human to human communication is a story. It's the incredibly versatile, somewhat scalable unit by which we teach each other meaningful experiences. Our brains recorded stories well before any hints of our ability to draw and write. We sit around a table or campfire sharing stories, not mere facts. We … Continue reading Stories are the Transactional Unit of Human-Level Intelligence →

Reptile Intelligence: An AI Summer for CEP

Complex Event Processing AI doesn’t emerge from a hodgepodge of single-function models—a decision tree that predicts churn, or a neural net that classifies an image, which only see one quality of the world. The AGI-level intelligence that's being frantically chased requires massive, organized integration of learned rules. That is, a large, heterogenous number of composed … Continue reading Reptile Intelligence: An AI Summer for CEP →

The Ghost of OLAP Aggregations – Part 2 – Aggregation Manager

This is Part 2 of a 3-part series where I make the case that pre-aggregated OLAP is essential in this era of AI. The intent of this post is to describe just enough of how a pre-aggregated OLAP engine works for those who are unfamiliar with this technology: Those who have joined the business intelligence … Continue reading The Ghost of OLAP Aggregations – Part 2 – Aggregation Manager →

Outside of the Box AI Reasoning with SVMs

The phrase “thinking outside the box” traces back to a deceptively simple puzzle: nine dots arranged in a 3×3 grid. The challenge is to draw four straight lines through all the dots without lifting your pencil. Most people fail at first because they instinctively keep their lines inside the square boundary implied by the dots. … Continue reading Outside of the Box AI Reasoning with SVMs →

Correlation is a Hint Towards Causation

Long ago when scaling database capacity wasn't as easy as upping (or downing) configuration settings through a user-friendly admin Web page (like the "T-shirt size" with Snowflake), highly-skilled DBAs were a luxury at smaller enterprises, and people at work used to go to Happy Hour in droves, a funny thing might happen at pau hana … Continue reading Correlation is a Hint Towards Causation →

The Ghost of OLAP Aggregations – Part 1 – Pre-Aggregation

If your entry into the business intelligence (BI) game began after around 2010, it could be difficult to appreciate the value of OLAP cubes (referring mostly to SQL Server Analysis Services MD, ca. 1998-2010), those aggregations, and that MDX query language. In fact, you may have a negative impression of those relics, those "cubes", based … Continue reading The Ghost of OLAP Aggregations – Part 1 – Pre-Aggregation →