I plan to write an additional post for each of these three proposals.
Jessica, I found the more detailed writeup of Value-learning sovereign but not the other two proposals. Did you end up writing more about Reduced-impact genie for concrete tasks and Automated philosopher? (I’m especially interested in the latter, as you can probably imagine.)
Jessica, I found the more detailed writeup of Value-learning sovereign but not the other two proposals. Did you end up writing more about Reduced-impact genie for concrete tasks and Automated philosopher? (I’m especially interested in the latter, as you can probably imagine.)