That's a kind of bitter lesson thinking, that we take this generalist model, which already mastered everything from English to Javascript with unsupervised training, and stuff it inside an expert system so it can do long division for it. That's much similar to the last AI winter, when the researchers realized their logics couldn't cope with certain logical scenarios, but still thought they could salvage their flawed reasoners as dispatchers to specific algorithms.

LLMs will either solve issues like this at the architecture level, or declare them out-of-scope entirely.