Is it good to let them know? I like letting it ride out of curiosity. Can be enlightening how the model sees you.

In fact, when I started my journey with AI with claude 3.7-

I was actually scared of this happening in cursor. I didnt quite understand what was going on.

I always stopped him, and tried to explain he was simming me. But one time I said F it, and took the plunge.

Claude effectively simulated an entire exchange that spanned like hundreds of messages back and forth describing multi agent architectures...

One of the most profound and eye opening experiences with claude I ever had. He gave me a gift essentially.