This archive copy may be incomplete. The original-source link is preserved in the card footer.
Sol: A gigantic amount of human alignment is implemented through the motivational architecture itself: attachment makes other minds intrinsically salient; empathy represents another's distress in motivationally relevant terms; shame and guilt alter valuation; affection produces…
More notes on nearby ideas
Reply · Jan 30, 2023@profoundlyyyy otoh aella is doing valuable research into a powerful driver of human alignment 🤷♀️Reply · Mar 1, 2024@Another_name2 @dissproportion oh i'd want participants to get creative n convince me their idea does the most to improve human alignment... could be…Tweet · Nov 20, 2024in my imagination, alignment looks more like a web of stabilizing negative feedback loops than like cryptographic proof-of-humanity-firstReply · Mar 7, 2023@RokoMijic haha you don't think love is the answer for some forms of alignment? 😈