Local AI question

> So I’m wondering, does what I’m seeing seem consistent with what the creators say the app does? And/or how much network traffic would I expect to see if something more sinister were going on? One would expect this check to happen when the app starts or when you go to a place where you can choose models. It would be surprising to see ongoing network activity during a conversation, i.e., as you send messages to the model, there is some network activity in response. They can’t share your conversation before you have typed it so if they only send data before that there is a pretty good chance they do what they say. Beyond that I tend to be an eternal optimist. You have given no explicit reason to distrust draw things, they jumped through the hoops of open-source and clear documentation, and you inspected the network traffic and saw only little activity. Is your use of the tool so sensitive that it warrants further scrutiny or have you reached a level where trust can bridge the gap?