DD, Not Desensitization

I think Google published a paper pretty recently about how large language models can self-improve. So, I think there's something fascinating there that's worked on packing. The other thing you were saying, I'm just going back to the program, an example for a sec. Because we'll actually have a real version of the medical conversation when we talk about customer support. It's almost like you're telling it how to think about things or you're giving it new information and then not forcing it to reconsider its opinion. What's happening there? And like, we've got to talk right at the cutting edge here.