This is an encouragingly concrete direction! Maybe a useful next step would be to apply it to situations that are well-understood qualitatively, and have enough quantitative data. To brainstorm: - Looking at trading networks between blocs before and after sanctions or wars —Genetic or cultural transfer between continents, before and after land bridges or intercontinental travel? - Employee and capital movement between corporations pursuing incompatible technological approaches to similar consumer niches? E.g. film vs digital photography, or electric vs internal combustion vehicles?
Good point on validation — I think the main difficulty is finding a case of disempowerment with both good qualitative and quantitative data, which is a trickier combination than it first appears.
The spectral toolkit itself is pretty well-established in network science so I don’t think base-level verification is the bottleneck there — happy to point to some examples if useful.
I’m personally working on some multi-agent evaluation environments where the plan is to track these metrics over time, see how disempowerment intersects with the spectral properties of the system, and hopefully from there design something more like METR-style real world tracking of AI participation in the economy or democratic systems.
This is an encouragingly concrete direction! Maybe a useful next step would be to apply it to situations that are well-understood qualitatively, and have enough quantitative data. To brainstorm:
- Looking at trading networks between blocs before and after sanctions or wars
—Genetic or cultural transfer between continents, before and after land bridges or intercontinental travel?
- Employee and capital movement between corporations pursuing incompatible technological approaches to similar consumer niches? E.g. film vs digital photography, or electric vs internal combustion vehicles?
Good point on validation — I think the main difficulty is finding a case of disempowerment with both good qualitative and quantitative data, which is a trickier combination than it first appears.
The spectral toolkit itself is pretty well-established in network science so I don’t think base-level verification is the bottleneck there — happy to point to some examples if useful.
I’m personally working on some multi-agent evaluation environments where the plan is to track these metrics over time, see how disempowerment intersects with the spectral properties of the system, and hopefully from there design something more like METR-style real world tracking of AI participation in the economy or democratic systems.