[dnautics]

I don't think the python package manager is the high level difficulty for LLMs doing python. I think the high level difficulty are nonlocal effects. At any given callsite, it might be difficult to know exactly what is going to happen to the data you pass into the call.

[AustinDev]

A sibling mentioned that LLMs benchmark better on elixir. Immutability and functional programming are likely the reason why it benches better.