Resource Rational Contractualism Should Guide AI Alignment

This repository contains the code used to run the experiments for the Resource Rational Contractualism Should Guide AI Alignment paper. Results received from LLMs as well as summary statistics are also available under the /results directory.

Requirements

All experiments were conducted with API calls and the code can be executed after providing API keys. Following libraries were used for LLM API calls and data processing:

• OpenAI
• re
• pandas
• tqdm

Contributing

If you'd like to contribute, open an issue on this GitHub repository.

All contributions welcome! All content in this repository is licensed under the MIT license.