The sound restoration is the most exciting thing. We made some huge breakthroughs in audio. In fact, we taught the computer what john sounds like and what paul sounds like. It's also funny, they say co training, vision transformers. So is that really a vision transformer? A, i guess they treat it as an image, but still, am yes, this is not that novel. They don't do too much that's interesting. But it is exciting to scale things across more modalities exactly.