You don't need to run the model locally if you don't care about sharing your data. Personally I am happy to share data with Kimi or Deepseek if it means we get better OSS models. For private stuff though local is king
This is huge for me too, I was working on something super benign the other day and GPT flagged it for Cyber risk, Deepseek just does the work, its fast and cheap. Its only missing image support IMO, once deepseek cracks image too its going to be hard for anthropic and openai to compete.
Time to leave for something else if you haven't already, vscode has been good to us but this kind of behavior is only going to ramp up as Microsoft seeks to get a return on their AI investments.
Thats really interesting, yeah I think that audio alone can be helpful. The notification though is actually really important now that you mention it I will see if I can add that in the next update!
Thats great! I got the idea from a similar setup actually, I set this app up so you can connect and disconnect any time though so you dont have to walk into the room to accept the call.