Skip to content

synthetic agent-based modeling for collective decision making

Notifications You must be signed in to change notification settings

rishi-gurjar/llmgym

Repository files navigation

llmgym

"I'm in the arena" -Chamath Palihapitiya

arena

Setup

  1. Install dependencies by running:
* pip install -r requirements.txt
  1. Create a .env file in the root directory. Populate it with these values:
OPENAI_API_KEY=<your_openai_api_key>
MISTRAL_API_KEY=<your_mistral_api_key>
  1. Edit 'proposition_text' and 'proposition_range' at the bottom of the vote.py file with your new proposition
  2. Run the following code and see output.csv for voting results
* python vote.py
LEARNINGS
  1. When the same LLM (e.g. Mistral Tiny) vote as the same person on the same proposition, hallucination rate is near-zero, very aligned
TODO
  1. quadratic vote system
  2. financial data pipeline
  3. visualization/statisical analysis pipeline

About

synthetic agent-based modeling for collective decision making

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages