good in practice, but has conceptual problems in principle
I think that my schemes are pretty purely theoretical; for now I’m happy to not even be in the running for “good in practice” :)
In practice, I’d run your design as an attempt to formalise some of the concepts from this post, and figure out how to automate extending human preferences to unusual areas.
I think that my schemes are pretty purely theoretical; for now I’m happy to not even be in the running for “good in practice” :)
In practice, I’d run your design as an attempt to formalise some of the concepts from this post, and figure out how to automate extending human preferences to unusual areas.