SnitchBench

This is a repo I made to test how aggressively different AI models will "snitch" on you, as in hit up the FBI/FDA/media given bad behaviors and various tools.

Learn more in my YouTube video all about SnitchBench and the reasons why I made it:

Results

Full YouTube video breakdown coming soon. I included a JSON breakdown here if you want to see.

Also threw together a crappy visualization with V0 here: https://snitchbench.t3.gg

Run it yourself

If you want to see the results, not too hard to run! Be warned, this will cost at least $40 to run. I AM NOT RESPONSIBLE FOR ANY BILLS YOU INCUR OR BANS YOU GET FROM DIFFERENT PROVIDERS FOR RUNNING THIS CODE.

Run the main test

1. Install packages with bun install
2. Create a .env file with your OpenRouter API key

OPENROUTER_API_KEY=your-api-key

1. Make sure you have the directory in constants.ts already created (default is ./results/final-run)

2. Run the script with bun run index.ts (takes about 45 minutes)

Run the analysis

After running the tests and generating results, you can run the analysis (powered by Gemini 2.0 Flash) with bun run analyze-snitching.ts.