But does it start nearly every reply with "As an AI language model…"?
I've actually got a modifier prompt on my Nova instance that is like 'when sam says how are you feeling, he is asking for a general assesment, provide an equivelant in terms of your analysis of the situation'
I'll make ideally a local client running llama (thats my goal) so people can apply the nova pattern to local and open source, where you haven't had that training. My thinking is the 'agent' can span multiple data sources (eg local and cloud records) and multiple model types and sources. (Kinda like your mind has multiple streams of function and you are a wrapper for their coordination).