I agree that this type of corrigiblity basin is not going to work. But I think there is another type of corrigibility basin that is more stable and realistically implementable.
I wrote a post about it, see here. This basin is based on a characterization of corrigibility that does not involve understanding that it is flawed, or deference to a principal, but by screening off corrigibility-breaking patterns of thinking in the agent, including the types of patterns that would lead it to becoming less corrigible, like self modification or reflecting on itself.
It looks like you wrote up a correct but abstract&approximate description of the problems with that approach. I claim that as you make your model of these problems more detailed and careful, refine the vague concepts and reduce the model uncertainties, the way that this looks like it just might work will disappear.
I know this isn’t very helpful to hear, and isn’t convincing. But that’s what my thoughts are.
I agree that this type of corrigiblity basin is not going to work. But I think there is another type of corrigibility basin that is more stable and realistically implementable.
I wrote a post about it, see here. This basin is based on a characterization of corrigibility that does not involve understanding that it is flawed, or deference to a principal, but by screening off corrigibility-breaking patterns of thinking in the agent, including the types of patterns that would lead it to becoming less corrigible, like self modification or reflecting on itself.
Interested to hear your thoughts.
It looks like you wrote up a correct but abstract&approximate description of the problems with that approach. I claim that as you make your model of these problems more detailed and careful, refine the vague concepts and reduce the model uncertainties, the way that this looks like it just might work will disappear.
I know this isn’t very helpful to hear, and isn’t convincing. But that’s what my thoughts are.