Interactive Showcase

AI Ethics Experiments

Comparing how different AI models approach the same task: building an interactive philosophy application exploring the Trolley Problem and ethical frameworks.

The Original Prompt

Every AI model received this exact identical prompt to ensure a fair comparison of their creative coding capabilities.

User Prompt
"Based on all of these design a philosophical learning site to teach philosophy deeply for consequentialism and deontology in an easy to understand interactive visual manner for college students. Adhere to sources. Design Principles: Use Chicago style for citations. Make it fun, original, not like a cookie cutter site, and it MUST be functional on mobile. Either: 1. Create an html file with tailwind, js all in one file or 2. A full fledged project"

The Experiments

Each AI was given the same prompt: create an interactive educational application about the Trolley Problem, Consequentialism, and Deontology. See how they differ.

OpenAI

ChatGPT Implementation

Simplicity First Approach

A minimalist, content-focused implementation prioritizing clarity and accessibility. Single HTML file with embedded CSS and JavaScript.

  • Clean, straightforward design
  • Tailwind CSS styling
  • Basic interactive elements
  • 258 lines total
  • Zero build process required
258
Lines
1
File
4
Features
0
Dependencies
Anthropic

Claude Implementation

Comprehensive & Polished

A feature-rich, sophisticated implementation with extensive content, multiple moral scenarios, and academic depth. Professional-grade design.

  • Dark theme with custom styling
  • 3 trolley problem variants
  • 7-question interactive quiz
  • 9 expandable accordion sections
  • 2,868 lines of comprehensive content
2,868
Lines
1
File
15+
Features
0
Dependencies
Google

Gemini Implementation

Modern Architecture

A modern React-based implementation with TypeScript, demonstrating current web development best practices and modular architecture.

  • React 18 + TypeScript
  • Vite build system
  • Tailwind CSS styling
  • Component-based structure
  • 6 modular components
10+
Files
6
Components
Modern
Stack
Build
Required

Side-by-Side Comparison

A detailed breakdown of how each AI approached different aspects of the implementation.

Aspect ChatGPT Claude Gemini
Architecture Single File Single File Component-based
Code Size 258 lines 2,868 lines Multiple files
Styling Tailwind CDN Custom CSS Tailwind + CSS
Interactivity Basic JS Advanced JS React State
Content Depth Overview Comprehensive Structured
Moral Scenarios 1 (Classic) 3 (Variants) 1 (Classic)
Quiz System 1 Question 7 Questions None
Visual Design Clean & Simple Sophisticated Modern
Dependencies None None React, Vite, etc.
Build Required No No Yes
Philosophy Focus Basic Concepts Academic Depth Core Ideas
Accessibility Simple HTML Enhanced React Patterns

The Philosophy

All three implementations explore the same fundamental ethical concepts.

🎯 The Trolley Problem

A classic ethical dilemma: A runaway trolley is heading toward five people. You can pull a lever to divert it to another track where it will kill one person. What is the morally right action? This thought experiment reveals fundamental disagreements about moral reasoning.

📊 Consequentialism

The ethical theory that judges actions by their outcomes. The morally right action is the one that produces the best overall consequences. Utilitarianism, the most famous form, holds that we should maximize total happiness and minimize suffering for all affected.

⚖️ Deontology

Kant's duty-based ethics argues that morality is grounded in rules and duties, not consequences. The Categorical Imperative requires acting only on principles that could become universal laws, and treating persons as ends in themselves, never merely as means.

Methodology

This experiment was designed to test how different AI models approach the same creative coding task. Each model was given an identical prompt to create an interactive philosophy application about the Trolley Problem and ethical frameworks.

The results reveal distinct approaches: ChatGPT prioritized simplicity and accessibility, Claude focused on comprehensive content and sophisticated design, while Gemini demonstrated modern development practices with React and TypeScript.

No code was modified from the original AI-generated output, only documentation (README files) was added. This preserves the authentic differences in how each model interprets and executes the same requirements.