Blog

Technical Writing

Deep dives into the engineering tradeoffs behind the systems I ship.

April 16, 2026|4 min read

The Danger of "Sounding Right": Understanding AI Hallucinations

AI doesn't tell you when it's guessing. It generates text that sounds right instead of text that is right. What hallucinations look like, why they happen, what goes wrong when you trust them in high stakes work, and how to engineer around them.

AI SafetyLLM SystemsHallucinationsResponsible AIPrompt Engineering

April 15, 2026|2 min read

Why a Mathematics Degree Is the Ultimate Cheat Code for a Career in Tech

The Calc 2 wall is where most tech kids quit. The ones who push through and finish a math degree walk out with the most flexible, future proof ticket into software, data, and AI.

CareerMathematicsTechAIEducation

February 20, 2025|6 min read

How I Built a Pipeline That Stops LLMs from Hallucinating, Using the Strategy Pattern

LLMs hallucinate. In a compliance pipeline, one hallucinated AWS service name can taint an entire audit trail. Here's how I stopped trusting the model as an oracle and rebuilt it as a scoped classifier wrapped in deterministic code that doesn't negotiate.

AI SafetyLLM SystemsPythonPrompt EngineeringStrategy Pattern