This archive copy may be incomplete. The original-source link is preserved in the card footer.
RT @Plinz: The question of how to align ASI comes approximately down to “what would I do if I was infinitely smart?”. I don’t trust people…
More notes on nearby ideas
Reply · Apr 3, 2023"even a superintelligent AI can face the alignment conundrum how to learn human values without misinterpreting them like a digital King Midas turning…Reply · Apr 3, 2023@RokoMijic so, when you assume ASI will immediately grab any resources it wants on the basis of intelligence alone.....? 🤔Reply · Apr 5, 2023@RokoMijic @CircuitCorroder lol you realize all my behavior is premised upon the assessment by a MIRI person that I'm too dumb to make any difference…Reply · Nov 18, 2022@GSSPmusic @banks10v24 Yeah, imo greater intelligence means seeing the pattern behind things which turns into rule of thumb to apply in future…