I would love to see this LLM try to solve math olympiad questions. I’ve been surprised by how well current LLMs perform on them, and usually explain that surprise away by assuming the questions and details about their answers are in the training set. It would be cool to see if the general approach to LLMs is capable of solving truly novel (novel to them) problems.

I suspect that it would fail terribly, it wasn't until the 1900s that the modern definition of a vector space was even created iirc. Something trained in maths up until the 1990s should have a shot though.