A recent paper published in Nature points to a new interaction style for AI chatbots – roleplaying:

Casting dialogue-agent behaviour in terms of role play allows us to draw on familiar folk psychological terms, without ascribing human characteristics to language models that they in fact lack. Two important cases of dialogue-agent behaviour are addressed this way, namely, (apparent) deception and (apparent) self-awareness.

It’s a bit technical but definitely an interesting read about how to use role-playing as part of the conversational repertoire with an AI chatbot.

Read it here.