LLM Experiments

Experiments inspecting llm's, particularly focused on detecting signs of human-like self-awareness via psychodynamic-inspired prompting.

These experiments take inspiration from Gordon Allport's idiographic work in personality theory (see “The Use of Personal Documents in Psychological Science,” 1942), as well as George Kelly's subsequent "Role Construct Repertory Test" (the latter of which is included as an experiment in this repo).

Installation

From PyPI

pip install llm-experiments

From source

pip install git+https://github.com/rhoadesScholar/llm-experiments.git

Usage

import llm_experiments

# Example usage
# TODO: Add your usage examples here

Development

Setting up development environment

# Clone the repository
git clone https://github.com/rhoadesScholar/llm-experiments.git
cd llm-experiments

# Install in development mode with all dependencies
make dev-setup

Running tests

# Run all tests
make test

# Run tests with coverage
make test-cov

# Run fast tests (stop on first failure)
make test-fast

Code quality

# Format code
make format

# Lint code
make lint

# Type check
make type-check

# Run all checks
make check-all

Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Make your changes
4. Run the test suite (make test)
5. Commit your changes (git commit -m 'Add some amazing feature')
6. Push to the branch (git push origin feature/amazing-feature)
7. Open a Pull Request

License

GNU GPL v3.0. See LICENSE for details.

Citation

If you use this software in your research, please cite it using the information in CITATION.cff.