So we're super excitedan,

by the way, everyone on here is under c d. You can go and now as much. Sha ha ha. Aeoin or hartget ard, thenext, the

next feater, we'll have to ask paul to build up here. An auto sacevetendis, that

is funny. You know, when we think about this, we often contrast where we are, a big hat, which is really focused in this molecular engineering side, you know, making therapeutic agents. And that's yo. Obviously we have to have a thing we're trying to modify so that we hat. We're depend on targets, just like everybody else in the pharmosutical space. Um. But what we whats interesting is there really is a, there's, there's a view, i think, out in the community in bio farma, that sort of targets or everything, and targets where the value is. And the thing that's funny about that view is that there are a lot of things where the targets are given and they're never going to get any bettero canceris a good example. Like there's just recurrently mutated things. That's what we're going to have to live with. We're going to have to figure out how to use the common mutations, for instance, te caras or other things that really are the hall marks of human cancers. And the story making advances in cancer therapeutics is largely one of getting more and more effective molecular designs, not necessarily discovering new targets, because the targets are pretty well understood. And that's true and a surprisingly large amount of areas. And if you want to manipulate the immune system, we have basically a full list of all the sido kinds and all their receptors. And and the challenge is not to discover some secret new sito kind that nobody knows about yet that controls everything, but in fact, to make good useinte ent, sophisticated use, of the actual molecules that we already know about. It's fascinatindg imat the opportunity there. Init's so vast am a couple of sort of questions on the company buildingside, and really just the future that i av serio super curious about a, you know, we have these, you know, this running joke at thee, at the bi on the bile team here at ston z, where we talk about, like, thi fictional future biote start up, right where, which we call miami beach biote. I may have added the miami. You may have at miami beach biote. This place is amazing. O. Employees can sit with a laptop on the beach perform everything you need to do for drug design through some combination of machine learning and biophysical simulation and, you know, robodicized experiments and really just external, external development and manufacturing services that you just run everything off o a machine, off of a laptop. How far away are we from that future? Likeow, how much do we need to be integrated with and closely andt integrated with the wet, squishy stuff in the wet lab? You

know, i actually don't think we're that far away. And i think this is kind of a, we had never thought about it as y maami beach by ota, but i think we are. Sand carlo by attacgod tooheas t the baylands aren't quite as i don't say beautiful and sandy, but i still love them. A, ya, i think we

oughter shed water that very cold.

A, the weather is good. We think about this a lot, actually, and i think, like just how it is, the more you can scale towards that vision. And i think that vision is not just the sitting on the beach, but essentially, like having all the machinery you need to actually do this effectively, while not local. I think it's huge. And is also just huge for big head as we grow. In particular, you know, what that really means is that, if you are able to do that, that means you have a highly controlled and highly reputable process cess. And this is what we really care about, right? When we bild a platform, we think about, how do we think about all the sort of steps, all these modules we talked about, and kind of, you know, i guess all the sort of variancs that they they induce, right? If you have a lot of people coming in, if you have diffent environments, difernt humidities, different temperatures, you are producing molecules, you know, there can be a lot of a lot of a sort o variance or disruption. And in the process. And i think the more that you can make am a kind of an autom ted and hands off version that's really run by robotics, by automation, and not just with people, ah, but sort of scales the output through machinery, you get closer to this vision. And you don't just get closer to this vision of sitting on the beach. You get closer to the vision of deep control of your data, about being able to run many kind of programms a simultaneously with, you know, high confidence in the quality that you'll be able to produce, a high confidec in the ability to integrate data, because you know with high confidence that the processes that produce that data, you know, i think were were performed many times over and in the exact same way, and you can combine them and, and, you know, also, your employers are happy, right? Case iy, consider the beach withthepina clata. But i think most importantly, you know, this really, it puts it a good forcing function on development of something like a the big hat platform. And we're really excited by that vision.