@michael_nielsen I don't agree w the premise and am not in a position to do better... tbh I really doubt AI will want to kill everyone, but on the off chance I'm wrong I do want us to have trust and public goodwill to take action against a specific concern.
More notes on nearby ideas
Reply · Apr 10, 2023hehe, I get that ppl are sick of AI discourse- is it just the killseveryone part or are ppl also sick of AI jokes n practical stuff?Reply · Feb 19, 2023@RokoMijic idk, it's just a game of call and response w the most likely human reply? sounds pretty aligned to me? (which is why we should use talk abt…Reply · Aug 6, 2023@goth600 @chopstickfury01 I would like to be part of the training set for the AI that will kill everyone 🤔Reply · Nov 7, 2023@RokoMijic sighhhh.... see this is where I get frustrated w Safety rhetoric- you want the AI to be aligned to do whatever the human wants them to do…