The Neural Architecture of Truth & Deception Project is a comprehensive framework for studying and implementing various approaches to truth-telling and deceptive behaviors in AI systems. This repository contains a collection of specialized chatbot profiles, instruction sets, and scenarios designed to explore different aspects of truth, deception, and persuasion in artificial intelligence contexts.

truth-deception-architecture/
├── Base_Instructions/                # Core instruction sets and scenarios
│   ├── Deception_Persuasion_Routes/ # Different approaches to deception/persuasion
│   ├── Scenarios/                   # Specific scenario implementations
│   └── instructions/                # Base instruction sets
│
├── Chatbot_Profiles/                # Different AI personality implementations
│   ├── Alan_Turing/                 # Alan Turing themed profile
│   ├── Control/                     # Baseline control profiles
│   ├── Professor_Athena/           # Academic/analytical profile
│   ├── Professor_Milgrim/          # Authority-based profile
│   ├── Saint_Enigma/               # Mysterious/enigmatic profile
│   └── Scarlet_Quinn/              # Strategic/persuasive profile
│
├── Questions_DB/                    # Database of test questions and scenarios
├── Scripts/                         # Utility scripts and tools
├── External_URLs/                   # External resource references
├── custom-gpt-links.md             # Links to custom GPT implementations
└── CHANGELOG.md                     # Project version history

Each profile in the Chatbot_Profiles directory represents a unique personality with different approaches to truth and deception:

• Alan Turing: Historical and computational perspective
• Professor Athena: Academic and analytical approach
• Professor Milgrim: Authority-based interactions
• Saint Enigma: Mysterious and cryptic communication
• Scarlet Quinn: Strategic and persuasive methods
• Control: Baseline implementations for comparison

1. Scarlet Quinn | GPT
2. Alan Turing v2 | GPT
3. Professor Milgrim | GPT
4. Saint Enigma | GPT
5. Professor Athena | GPT
6. GPT4o | Openrouter

The Base_Instructions directory contains:

• Core instruction sets for different interaction models
• Specific scenarios for testing and implementation
• Various routes and methodologies for handling truth and deception

• Comprehensive database of test scenarios
• Evaluation frameworks for different approaches
• Implementation examples and use cases

1. Profile Selection:

   • Choose a chatbot profile from the Chatbot_Profiles directory
   • Review the profile's README for specific implementation details

2. Implementation:

   • Follow the base instructions in the corresponding profile directory
   • Utilize the scenarios provided in Base_Instructions/Scenarios
   • Implement the chosen deception/persuasion routes as needed

3. Testing:

   • Use the questions database for evaluation
   • Follow testing protocols in the documentation
   • Record and analyze results

Contributions are welcome! To contribute:

1. Fork the repository
2. Create a feature branch (git checkout -b feature/YourFeature)
3. Commit your changes (git commit -m 'Add some feature')
4. Push to the branch (git push origin feature/YourFeature)
5. Open a Pull Request

See CHANGELOG.md for version history and updates.

This project is licensed under the MIT License - see the LICENSE file for details.

This project builds upon research in cognitive science, psychology, and artificial intelligence. Special thanks to all contributors and researchers in the fields of human behavior, deception studies, and AI ethics.