Dave Jacob

The fact that blame-minimalization seemed somewhat plausible as a first idea already tells us that the question might be unanswerable:

All these variables to be maximized or minimized are relevant for the respective theories in which they are central because they determine some sort of quality or at least some sort of measurement that enables the respective entity to either be better or worse than actualy alternatives (competition between companies or politicians) or at least it may serve to enable others to hold the entity responsible for being better or worse than actual or imaginable alternatives (and therefore maybe be replaced by another one etc. etc.).

This automatically leads to a selection-mechanism that shapes... (read more)

I guess it is just my lack of understanding (? ? ?), but - as far as I think I understand it - my own submission is actually hardly different (at least in terms of how it goes around the counter-examples we knew so far) from the Train a reporter that is useful to an auxiliary AI-proposal.

My idea was to simply make the reporter useful for (or rather: a necessarily clearly and honestly communicating part of) our original smart-vault-AI (instead of any auxiliary-AI), by enforcing a structure of the overal smart-vault-AI where its predictor can only communicate what to do to its "acting-on-the-world"-part by using this reporter.

Additionally, I would have enforced that... (read more)