How to Refine the Performance of the Data Sources

So to sort of recap, we start off with a decision tree esque label structure. That is autocomplete for people who are going to be labeling or suggested results. And then iteratively, we increase the complexity of the model as the labelers label more data. Is that more or less the the one minor? Yes. So the, so I think if we need to, if you want to just keep in mind two things. The first thing is you need to do it like any smaller versions on your level. And the second thing is you cannot, so there is no magic. There is no getting rich effect in the living project.