Executive summary: The post argues that human values related to “niceness,” boundaries, and liberalism are importantly different from the values of a “paperclip maximizer” AI, and suggests incorporating those human values into how we think about relating to AIs with different values.
Key points:
Unlike a paperclip maximizer AI that just cares about making paperclips, human values incorporate notions of “niceness” like respecting others’ autonomy and not violently overthrowing them even if they have different values.
Concepts from political liberalism around tolerance, diversity, and respecting individual rights and boundaries are also relevant to how humans should ideally interact with AIs with different values.
These human values likely have practical benefits too in terms of cooperation, attractiveness of society, etc. that are worth preserving with AIs.
However, some minimal versions of liberalism may not guarantee a flourishing future, so we still need to empower agents who care about human values like love and beauty.
This comment was auto-generated by the EA Forum Team. Feel free to point out issues with this summary by replying to the comment, andcontact us if you have feedback.
Executive summary: The post argues that human values related to “niceness,” boundaries, and liberalism are importantly different from the values of a “paperclip maximizer” AI, and suggests incorporating those human values into how we think about relating to AIs with different values.
Key points:
Unlike a paperclip maximizer AI that just cares about making paperclips, human values incorporate notions of “niceness” like respecting others’ autonomy and not violently overthrowing them even if they have different values.
Concepts from political liberalism around tolerance, diversity, and respecting individual rights and boundaries are also relevant to how humans should ideally interact with AIs with different values.
These human values likely have practical benefits too in terms of cooperation, attractiveness of society, etc. that are worth preserving with AIs.
However, some minimal versions of liberalism may not guarantee a flourishing future, so we still need to empower agents who care about human values like love and beauty.
This comment was auto-generated by the EA Forum Team. Feel free to point out issues with this summary by replying to the comment, and contact us if you have feedback.