Recommendation systems (e.g., Twitter) optimize for your attention and spoil you to the detriment of your own well-being. Their objective is fundamentally misaligned with yours.
We are developing an open source chrome extension RecAlign (short for Recommendation Alignment) to address this misalignment. We use large language models (LLMs) to vet and remove recommendations according to your explicitly stated preference in a transparent and editable way.
- Pin the extension on the toolbar.
- Click on the extension icon.
- Fill in your preference as well as your OpenAI API Key, which you can find here.
- Run
npm install
. - Run
npm run build
. - Compiled chrome extension now exsits at the
chrome-extension
folder. - Load the
chrome-extension
folder as unpacked extension.