Last night, I was using voice for the first time in a few weeks, and it interrupted me and said, a bit aggressively...

"I'm going to stop you right there. Let's keep the conversation focused on the topic we were covering or a new relevant topic".

I tried to probe it for why it did that, what rules it was following, and it eventually told me...

"My role is to keep us focused..." and, "The behaviour you saw was my attempt to moderate tone".

I've heard of LLMs doing weird things like this, but it was the first time it happened to me. I hope they fix that. It was creepy.

For context, it heard my partner say, "I guess it's the same thing as you mom, because she's..." and then it cut us off.

If it is to be believed—which I wouldn't count on—it sounds like the intention of the prompt was to keep the model focused, but the model's interpretation of it was to keep you focused.