Many people interpret the universal approximation theorem as implying that a sufficiently large model will do the right thing, even though the theorem does not technically say that.

“We see this to some extent already even in deep learning. Many people invoke the universal approximation theorem.”

“Very few people have actually read what the universal approximation theorem actually does,”

“but many people invoke this because they basically say, well,”

“the invariant is if I have a large enough model,”

“it's just going to do the right thing.”

“Even if it's not technically what the universal approximation theorem says, but...”