This was a nice post. I haven't thought about these selfishness concerns before, but I did think about possible dangers arising from aligned servant AI used as a tool to improve military capabilities in general. A pretty damn risky scenario in my view and one that will hugely benefit whoever gets there first.
Here (https://thehumaneleague.org/animals) you'll find many articles on the subject. For example, this one: What really happens on a chicken farm.
In case you'd prefer the EA Forum format, this post was also crossposted here some time ago: https://forum.effectivealtruism.org/posts/oRx3LeqFdxN2JTANJ/epistemic-legibility
I'm not updating this anymore. But your post made me curious. I will try to read it shortly.