Importantly it’s not just any model they’re “alloying”. It’s only the two most capable models where there’s objective evidence that the combination is better than the individual parts.
In this way, it’s not really a “lowest common denominator” as you get to pick the highest performing combination (with solo models just being a special case).
In humans, diversity of thought [patterns, not just diversity of knowledge] increases the quality beyond its parts.
I suspect this model alloy tactic always works, just only seems impressive when it does so with the top models and achieves otherwise unattainable quality.
One paper of many such new (and nuanced) wisdom of crowds resources:
In this way, it’s not really a “lowest common denominator” as you get to pick the highest performing combination (with solo models just being a special case).