@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 but also to not kill everyone but some humans ARE mass murderers, so it's a contradiction
More notes on nearby ideas
Reply · Feb 19, 2023@JCorvinusVR @skooookum lol yeah, AI safety's worst mistake was using the word "alignment" rather than "non-murderousness"Repost · Aug 21, 2025RT @RokoMijic: AI Safety could literally kill meReply · 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 · Jun 3, 2022@deepfates My biggest concern, personally, is that someone takes AI safety rhetoric very literally and decides to commit an act of terrorism that…