25 Comments
User's avatar
⭠ Return to thread
Sean Sweeney's avatar

Thanks for the post! I won't pretend to have followed everything in it, but I think you may find the alternate utilitarian framework I propose here to be interesting: https://www.lesswrong.com/posts/wwioAJHTeaGqBvtjd/update-on-developing-an-ethics-calculator-to-align-an-agi-to.

I expect the "Unique (I Think) Contributions" section would be most interesting to you. I believe my framework, with value based on "positive experiences" as influenced by self-esteem and with explicit incorporation of the effects of rights on value building may be something fun to debate with your "conceptually stunted" colleagues. Thanks! Sean

Expand full comment