I don’t think so. The listening and responding isn’t being managed by an LLM. That’s just the app listening with a microphone and timer.

Stop talking for x sec = process response.

I bet the bot would wholeheartedly agree that it would definitely wait for you to finish talking, then just not do it. It doesn’t know anything about the app it’s “in.” At least at a deep level.

I agree that all this is impressive, but with odd, unclear bounds that sometimes confuse users.