not to defend AI, but that is an expected outcome if you think about how LLMs work.

It tokenizes language to run math on it and send back processed natural-sounding language

of course it struggled with “how many rs in strawberry”

because

 r
 rs
 r's 
 how many r
 rs in 
 strawberry 
 in strawberry

would all present as different tokens of different length with different information spaces relative to them.

making a decision and having an opinion is not rude. And actually, often people are glad that you’ve removed the mental labor and discussion.