What's the role of both GPT-3 models and Jasper's fine-tuned models in generating content, and how do they work together?

Every different action in our product is hitting a different model. Some of them are shared models, but each one is going to be hooked up to a particular model that's going to go and actually receive the input and generate the output there. Some of them run through multiple models in a given run. 

We might do something first to clean it up or augment it and then go to GPT-3 next, or the reverse—it might be GPT-3 first, and then we clean it up with some of our own models. Generally, though, they're hitting either a foundation model or a fine-tuned model with any given action inside the product.