[ra]

Indeed. LLM is an application on a transformer trained with backpropagation. What stops you from adding a logic/mathematic "application" on the same transformer?

[seanhunter]

Nothing, and there are methods which allow these types of models to learn to use special purpose tools of this kind[1].

[1] https://arxiv.org/abs/2302.04761 Toolformer: Language Models Can Teach Themselves to Use Tools