This is fair. We're now evaluating open-source LLMs to develop our in-house solutions, adding them to our products and services. As soon as they released the models, the moat was, depending on the context, somewhat gone.
We're testing different models depending on the business case. Our initial tests using 3, 7, and 8B models are working fine. We're not using the big ones since our use cases don't demand them.
