When initialized from a basic vanilla transformer, Recursive's system outperformed the community's results.

“a transformer and so on and to actually combine these ideas and put them together that has then eventually also been invented but there's a knowledge cutoff and we did actually check that it didn't have access to that externally we talked about this a little bit if you scroll to the next figures you know this is also an interesting one in that when you start from a really basic poor like vanilla transformer then we still outperform all of the community”