We are updating the
alignment research dataset which will be used as a knowledge base for our chatbot to answer questions about AI safety and alignment. We are particularly looking to add individual articles, documents, videos, blog post published in 2022 or later that contain particularly high value content.
Here are some resources that are already in the dataset. If you have multiple sources that you'd like to update in bulk, DM ccstan on Discord with your gmail. Thanks in advance!