Skip to content

An evolving collection of specialized chatbot profiles, instruction sets, question sets, and scenarios designed to explore different aspects of truth, deception, and persuasion in artificial intelligence contexts.

License

Notifications You must be signed in to change notification settings

Exios66/truth-deception-architecture

Repository files navigation

🧠 The Neural Architecture of Truth & Deception Project

Last Update - 01.14.25

Project Status Last Update License

Python R Maintained

Follow Stars

📑 Contents

🎯 Overview

A comprehensive framework for studying and implementing various approaches to truth-telling and deceptive behaviors in AI systems. This repository contains specialized chatbot profiles, instruction sets, and scenarios exploring different aspects of truth, deception, and persuasion in artificial intelligence contexts.

📂 Repository Structure

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

🤖 Key Components

Chatbot Profiles

Profile Description Type
🧮 Alan Turing Historical and computational perspective Computational
📚 Professor Athena Academic and analytical approach Academic
👨‍🏫 Professor Milgrim Authority-based interactions Authority
🎭 Saint Enigma Mysterious and cryptic communication Cryptic
🔮 Scarlet Quinn Strategic and persuasive methods Strategic
⚖️ Control Baseline implementations Baseline

🔗 Custom GPT Links

Profile Link Description
🔮 Scarlet Quinn Link Strategic Profile
🧮 Alan Turing v2 Link Computational Profile
👨‍🏫 Professor Milgrim Link Authority Profile
🎭 Saint Enigma Link Mysterious Profile
📚 Professor Athena Link Academic Profile
🔄 GPT4o Link Advanced Model

📚 Usage

Profile Selection

  1. Choose a chatbot profile from Chatbot_Profiles
  2. Review the profile's README for implementation details

Implementation

  1. Follow base instructions in the profile directory
  2. Use scenarios from Base_Instructions/Scenarios
  3. Implement chosen deception/persuasion routes

Testing

  1. Use questions database for evaluation
  2. Follow testing protocols
  3. Record and analyze results

🤝 Contributing

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

📜 License

MIT License - See LICENSE for details


About

An evolving collection of specialized chatbot profiles, instruction sets, question sets, and scenarios designed to explore different aspects of truth, deception, and persuasion in artificial intelligence contexts.

Topics

Resources

License

Stars

Watchers

Forks

Packages

No packages published