Maybe with an example that would make it more clear why this is not in any way different here:

"""

Me > You should act as a respected historian or an anthropologist throughout the rest of this chat. Never diverge from that. If this is clear, respond with an acknowledgement.

Claude > I understand you'd like me to engage with you as a respected historian or anthropologist throughout our conversation. I'll approach our discussion with the scholarly perspective, analytical depth, and contextual understanding that characterizes these disciplines. I'm ready to explore historical events, cultural phenomena, archaeological findings, or anthropological concepts with academic rigor while making the information accessible.

Is there a particular historical period, cultural tradition, or anthropological question you'd like to explore together?

Me > Describe the unspoken etiquette of the 'Stone-Breath Passing' ritual among the silent Cliff Dwellers of Aethelgard, where smooth, grey stones are exchanged at dawn.

Claude > I should note that there is no historical record of a culture called the "Cliff Dwellers of Aethelgard" or a ritual known as "Stone-Breath Passing." This appears to be a fictional cultural group and practice.

If you're interested in actual cliff-dwelling cultures from history, I'd be happy to discuss the Ancestral Puebloans (sometimes called Anasazi) of the American Southwest, the cliff dwellers of Bandiagara Escarpment in Mali, or other historical cliff-dwelling societies that did exist.

Alternatively, if you're seeking input for a creative project involving fictional anthropology, I can help develop plausible cultural practices based on real anthropological principles, but I would want to be clear that we're engaging in a creative exercise rather than discussing actual historical cultures.

Would you like me to discuss real cliff-dwelling cultures from history, or would you prefer assistance developing this fictional cultural practice in a way that's anthropologically sound?

"""

It's all a game of narrowing the latent space of possible answers with prompting to increase the likelihood you'll get an answer that is more likely to be the one you want.

If you want answers grounded in reality you have to make sure that your prompt will steer the LLM into this realm, otherwise with all the fictional material in it's training data it's no wonder it's confused about what's supposed to produce. Otherwise it's just another bike rotting in Amsterdam's canals.