That is an incredible post. I strongly upvoted. Deals with a lot of arguments for AI doom. Very clearly written as well.
However, I do notice that there was nothing there about goal misgeneralisation or shutdown problem. Is it because 1) you’ve written about it elsewhere, 2) you believe that these problems have already been solved somewhere else, 3) you still endorse what you have written about them here or 4) you plan on writing about them in the future?
That is an incredible post. I strongly upvoted. Deals with a lot of arguments for AI doom. Very clearly written as well.
However, I do notice that there was nothing there about goal misgeneralisation or shutdown problem. Is it because 1) you’ve written about it elsewhere, 2) you believe that these problems have already been solved somewhere else, 3) you still endorse what you have written about them here or 4) you plan on writing about them in the future?