alt Hacker News> we'll see more specialized math AI resembling StockFish soon
Heuristically weighted directed graphs? Wow amazing I'm sure nobody has done that before.
> we'll see more specialized math AI resembling StockFish soon
Heuristically weighted directed graphs? Wow amazing I'm sure nobody has done that before.
My claim is that LLMs waste a lot of time training on all available data.
Math is a sequence of formal rules applied to construct a proof tree. Therefore an AI trained on these rules could be far more efficient, and search far deeper into proof space