Conversation

Question for my fellow alignment researchers out there, do you have a *list of unsolved problems* in AI alignment? I'm thinking of creating an "alignment mosaic" of the questions we need to resolve and slowly filling it in with insights from papers/posts. Gonna have a session on this in 2.25 hours. I have my own version of this, but I would love to combine it with others' alignment backcasting game-trees. I'm working with others to make this into a collaborative effort. DM for more detail. cc