So talk to me a little bit about, number one, how did that come about? But number two, just a little bit of definition before we go into the findings.

So the idea of synthetic data I think started in political science, to my knowledge, in 2023, and, um, initial studies saying, "Hey, maybe we could use LLMs to actually simulate people's opinions on political questions." And initially it was more telling the LLM, "Hey, behave as a Republican, you know, this age, th- this region, then here's a, a backstory, and then tell me how you would vote on this question." And so fascinating, uh, idea of being able to simulate, you know, human behavior.

Very quickly this got picked up in marketing, and so we started seeing-I think probably in 2023 or so, early papers saying that maybe we can do conjoint, for example, using synthetic respondents or, uh, other maybe perceptual maps and other types of market research.

So at the time it was mostly what I would call synthetic data, which is, uh, usually demographics and then maybe a short backstory, like a persona, and asking the LLM to behave like this synthetic, you know, person.

And so that's exciting, but we quickly found that the-- there's not maybe a lot of variation in the answers, and maybe sometimes there could be a bit of bias.

The model maybe tends to be systematically a Republican or Democrat, and then also some systematic biases.

Uh, so then the next evolution was, well, maybe if we can get more information on a given person, so I'm gonna maybe get a lot of data on Sima, and then I'm going to be able to create a twin, a dig- digital twin of Sima that is really going to mirror her behavior.

What's the driver here in terms of why people are so curious and excited about it?