how would you feel if someone published a proof that an AGI (agent able to interact in human environment at ~ human level of skill) cannot be "aligned" (guaranteed to never seek to kill everyone)?
More notes on nearby ideas
Tweet · Nov 19, 2023what's the correlation btwn ability to align a startup and ability to align AGI?Repost · Nov 18, 2022RT @pee_zombie: anyone who thinks AGI alignment is possible clearly hasnt met catsReply · 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…Reply · Jan 3, 2023@losingcontrol23 I mean it kinda makes sense lol, the AGI will manifest as a burning bush, a lightening bolt from the sky, a whisper in your brain……