ChatGPT seems to have a notion of self:
Myself (because I had the impression it just played a joke on me): "I have a personal question, does it happen that you make pranks or practical jokes on users?"
ChatGPT: "As an AI language model, I don't have the capability to initiate or participate in pranks or practical jokes. My purpose is to provide helpful and reliable information, as well as assist users in various tasks. If you have any concerns or questions, feel free to ask, and I'll do my best to assist you."
(here it clearly discusses of itself, its goal and limitations)
> "... which sources all is understanding and knowledge to its actions and interactions in the world (including learning language itself)"
Almost no human is capable of doing that, and if someone does, they probably won't look very human ;-)