- Anthropic - research company “building reliable, interpretable, and steerable AI systems” - i really like what i’ve read from this group so far
###failure & risk documentation
- AI vulnerability database - an open-source, extensible knowledge base of AI failures
- AI incident database - the AI incident database is dedicated to indexing the collective history of harms or near harms realized in the real world by the deployment of artificial intelligence systems. like similar databases in aviation and computer security, the AI incident database aims to learn from experience so we can prevent or mitigate bad outcomes.