I had instructions added too and it is doing exactly what you say. And it does it so many times in a voice chat. It's really really annoying.

I had a custom instruction to answer concisely (a sentence or two) when the question is preceded by "Question:" or "Q:", but noticed last month that this started getting applied to all responses in voice mode, with it explicitly referencing the instruction when asked.

AVM already seems to use a different, more conversational model than text chat -- really wish there were a reliable way to customize it better.