Semantic Precision and “The Butterfly Defect”

The Weight of Words

In human communication, we tolerate ambiguity. “Fast” could mean milliseconds or minutes. “User-friendly” means different things to different people.

AI doesn’t tolerate - it interprets. And propagates.

The Butterfly Defect

Traditional butterfly effect: A butterfly flaps wings in Brazil, causes tornado in Texas.

The Butterfly Defect: You type “modal” instead of “dialog”, your entire UI philosophy shifts.

Real example:

Human: "Create a service for handling user data"
AI: *builds microservice architecture*

vs

Human: "Create a class for handling user data"
AI: *builds single class with methods*

One word. Completely different architecture.

The Propagation Problem

Wrong terminology compounds:

• Say “component” → AI assumes React
• React assumption → hooks everywhere
• Hooks everywhere → state management complexity
• Complexity → performance issues

The defect spreads through every decision.

Finding the Right Words

Two strategies:

1. Use AI as Terminology Guide

Human: "What's the proper term for a popup window that blocks interaction?"
AI: "That's called a 'modal dialog' or simply 'modal'"

2. Define Terms Explicitly

For this project:
- "Service" means a class with business logic
- "Module" means a Python file
- "Component" means a logical grouping of features

Common Defects to Avoid

• “Simple” → AI removes error handling
• “Fast” → AI ignores correctness
• “Modern” → AI adds every new feature
• “Clean” → AI over-abstracts

The Precision Principle

Be specific about:

• Technical terms (service vs class vs module)
• Scope words (simple vs minimal vs basic)
• Quality attributes (fast vs optimized vs efficient)

Remember: AI amplifies ambiguity into architecture.

The Fix

When you catch a Butterfly Defect:

1. Stop immediately
2. Correct the terminology
3. Explicitly state what you mean
4. Let AI adjust course

“Fix your terminology now, or refactor your entire architecture later.”

Using a clearly named variables

Since AI understands variables also through their names, longer descriptive names are better than short cryptic ones.