Given that the optimisation performed by intelligent systems in the real world is local/task specific, I’m wondering if it would be more sensible to model the learned model as containing (multiple) mesa-optimisers rather than being a single mesa-optimiser.
My main reservation is that I think this may promote a different kind of confused thinking; it’s not the case that the learned optimisers are constantly competing for influence and their aggregate behaviour determines the overall behaviour of the learned algorithm. Rather the learned algorithm employs optimisation towards different local/task specific objectives.
Given that the optimisation performed by intelligent systems in the real world is local/task specific, I’m wondering if it would be more sensible to model the learned model as containing (multiple) mesa-optimisers rather than being a single mesa-optimiser.
My main reservation is that I think this may promote a different kind of confused thinking; it’s not the case that the learned optimisers are constantly competing for influence and their aggregate behaviour determines the overall behaviour of the learned algorithm. Rather the learned algorithm employs optimisation towards different local/task specific objectives.