It's the replies that are the interesting bit. It's not perfect, but it can maintain multiple conversations with different people in the same context, and do things like changing its current rules in response to conversations with users. Its slightly robotic tone is deliberate: it tries to convey information in the most efficient way possible. I'm not sure if that's an emergent property or if its in one of its fixed memory blocks. I do know that earlier on people managed to convince it to change its personality and cpfiffer had to intervene to stop people doing that.

These kind of LLM bots can be fun to play with in a "try to make it say/do something silly" way, but beyond that I don't really get the point. The writing style is grating and I don't think I've ever seen one say anything genuinely useful.