Recursive achieved these kernel results without spending months or years developing them, despite lacking deep CUDA-kernel expertise on the team.

“and basically they're only a handful of kernels in this whole benchmark where we weren't the best and so to me this is like really exciting because it makes it it just showcases what this can do and again these weren't like we didn't like spend months or years like developing in fact in particular for kernel cuda kernels like we don't even have really deep cuda kernel experts in the team”