Are there any interesting local versions of the OpenRouter "Fusion" or Sakana Fugu methods, being worked on, as of yet? I'm curious if these setups will enable us to use, say, a panel of various ~3...

Given how much of a boost in output quality these methods seem to enable when it comes to the big cloud models of having several smaller, cheaper models give output qualities on par with or higher than the strongest, Fable-class model, I am curious about how these things, of something similar to the OpenRouter Fusion system or Sakana Fugu system will affect local AI, of enabling us to use a cluster of various smaller local models together to get output quality more on par with the largest local SOTA models.