There's not even any point in that IMO. A model doesn't "know" things anyway everything useful it's going to get from tool calls and context.

I think the problem is up to date knowledge isn't really the difficult or useful bit. We're sort of moving to a world where the real value in training comes from tool calling and performance over long context - your models shouldn't really be relying on their internal knowledge, but instead calling various tools. But the performance gap between now and six months for that is pretty huge.