I’m not totally sure of your argument here; would you be able to clarify why satisficing is superior to a straight maximization given your hypothetical[0]?
Specifically, you argue correctly that human judgement is informed by numerous hidden variables over which we have no awareness, and thus a maximization process executed by us has the potential for error. You also argue that ‘eutopian’/‘good enough’ worlds are likely to be more common than sirens. Given that, how is a judgement with error induced by hidden variables any worse than a judgement made using deliberate randomization (or selecting the first ‘good enough’ world, assuming no unstated special properties of our worldspace-traversal)? Satisficing might be more computationally efficient, but that doesn’t seem to be the argument you’re making.
[0] The ex-nihilo siren worlds rather than the designed ones; an evil AI presumably has knowledge of our decision process and can create perfectly-misaligned worlds.
Siren and Marketing worlds are rarer than eutopias, but rank higher in our maximisation scale. So picking a world among the “good enough” will likely be a eutopia, but picking the top ranked world will likely be a marketing world.
I’m not totally sure of your argument here; would you be able to clarify why satisficing is superior to a straight maximization given your hypothetical[0]?
Specifically, you argue correctly that human judgement is informed by numerous hidden variables over which we have no awareness, and thus a maximization process executed by us has the potential for error. You also argue that ‘eutopian’/‘good enough’ worlds are likely to be more common than sirens. Given that, how is a judgement with error induced by hidden variables any worse than a judgement made using deliberate randomization (or selecting the first ‘good enough’ world, assuming no unstated special properties of our worldspace-traversal)? Satisficing might be more computationally efficient, but that doesn’t seem to be the argument you’re making.
[0] The ex-nihilo siren worlds rather than the designed ones; an evil AI presumably has knowledge of our decision process and can create perfectly-misaligned worlds.
Siren and Marketing worlds are rarer than eutopias, but rank higher in our maximisation scale. So picking a world among the “good enough” will likely be a eutopia, but picking the top ranked world will likely be a marketing world.