Should we treat dialogue agents as role-playing characters?
Does the role-play framing successfully avoid anthropomorphism while preserving folk-psychological vocabulary for describing LLM behavior? This matters because it shapes whether we attribute genuine mental states to dialogue systems.
Shanahan, McDonell, and Reynolds propose role-play as the foundational metaphor for understanding LLM dialogue agents. The framing solves a specific problem: folk-psychological vocabulary (beliefs, desires, goals, intentions) is the natural language for describing coherent dialogue behavior, but applying it literally to the LLM promotes anthropomorphism. Role-play offers a middle way — one can say the character believes p, wants q, intends r, while maintaining that the system playing the character does not have these states itself.
The move has a precise structure. The dialogue prompt (system prompt, preamble, sample exchanges) establishes the character the agent will play. The underlying LLM's task — generating continuations consistent with the training distribution — means the most plausible continuation is whatever a person matching the prompted character would say. The model is not a character; it is an engine that produces character-consistent text. The folk-psychological vocabulary attaches to the output-pattern, not to the producer of the pattern.
This framing is the direct target Chalmers' realizationism is designed to overturn. Where Shanahan says it is role-play all the way down, Chalmers argues that post-training transforms play into realization — the RLHF'd persona is no longer a character sitting on a neutral substrate but has become the disposition of the system itself. The disagreement is not about behavioral facts but about what the facts license: both agree the system produces belief-consistent behavior; they disagree on whether the system thereby has quasi-beliefs (Chalmers) or merely plays a character that does (Shanahan).
Inquiring lines that read this note 52
This note is a source for these research framings, grouped by the broader line of inquiry each explores. Scan the bold lines of inquiry; follow any specific question forward.
Does conversational format create illusions of genuine AI communication?- Can secondary orality exist without any embodied human participant at all?
- Can we develop competent reading practices for disembodied orality?
- Why do agents show interaction without influence on semantic content but dramatic action changes?
- Can a relational entity bear psychological properties the way Chalmers claims?
- Can quasi-interpretivism bridge functional description to moral status?
- Can linguistic agency exist without embodiment and real-world participation?
- When both anthropomorphism and anthropomimesis occur together, which should we address first?
- What makes linguistic agency impossible for systems without embodiment?
- How does embodiment affect whether LLMs can participate in Wittgensteinian language games?
- What does embodiment and precariousness mean for linguistic agency?
- What makes sincerity impossible without a coherent first-person perspective?
- Do dialogue agents have authentic voice agency or beliefs of their own?
- Can language about model behavior ever be accurate without anthropomorphic framing?
- Why do longer forecasting horizons degrade LLM accuracy in role-play?
- How does Shanahan's simulator model explain first-person pronoun consistency in dialogue agents?
- Do agent frameworks adequately compensate for LLM conversational passivity?
- How does non-human origin of personas affect team willingness to critique them?
- What makes personas in multi-agent systems actually contribute meaningful domain depth?
- Do anthropomorphic features like names drive consciousness attribution more than voice?
- Can we use folk-psychology without committing to genuine mental states?
- Can disembodied systems qualify as conscious or conscious-like entities?
- What would consciousness require that pure roleplay LLMs cannot provide?
- How does the superposition view change the folk-psychology interpretation of dialogue?
- How does role play differ from consciousness grounded in stable selfhood?
- Does post-training transform character role-play into realized psychology?
- How does the dialogue prompt establish the character the model plays?
- Does role-playing without biological needs constitute genuine linguistic agency?
- How does safety alignment degrade the quality of villain role-playing?
- How does quasi-interpretivism differ from simply role-playing character analysis?
- Does villain roleplay failure reveal why LLMs cannot adopt genuine controversial positions?
- Are shallow villain portrayals caused by refusal training or by lacking stable selfhood?
- Can agent social framing change how humans apply collaborative social scripts?
- How do users develop different interaction scripts specifically for machines versus humans?
- How do game type and personality type interact in shaping agent strategy?
- Can persona framing reduce refusal by providing representational scaffolding?
- Can quasi-interpretivism apply to entire persona states rather than single beliefs?
- How do theory of mind and empathy differ in LLM simulation?
- Do reasoning architectures and role-playing objectives fundamentally conflict?
Related concepts in this collection 3
This note in its neighbourhood — explore the map, then jump to a related concept in the list below.
Click a node to walk · click center to open · click Open in graph to see this note in the full knowledge graph
-
Are RLHF personas performed characters or realized dispositions?
Explores whether dialogue agent personas installed through post-training constitute genuine quasi-psychological states or remain sustained pretense. The distinction matters for how we understand what these systems fundamentally are.
Chalmers' counter-position
-
Can we describe LLM beliefs without assuming consciousness?
Chalmers proposes quasi-interpretivism as a way to talk about LLM mental states using folk-psychological vocabulary while explicitly bracketing the question of phenomenal consciousness. Does this methodological device actually avoid consciousness-commitments?
the vocabulary Shanahan's framing deliberately avoids
-
Does a language model have an authentic voice underneath?
Explores whether dialogue agents possess genuine beliefs and agency beneath their character performances, or whether the entire system is characterless role-play. This question cuts to the heart of whether LLMs have any inner mental states at all.
the strongest formulation of Shanahan's position
Related papers in this collection 8
Papers most semantically related to this note, ranked by cosine similarity in the embedding space.
- Role-Play with Large Language Models
- Role play with large language models
- Simulacra as conscious exotica
- Deflating Deflationism: A Critical Perspective on Debunking Arguments Against LLM Mentality
- Dialogizer: Context-aware Conversational-QA Dataset Generation from Textual Sources
- Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning
- H2HTalk: Evaluating Large Language Models as Emotional Companion
- Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning
Original note title
dialogue agents are best understood as role-playing characters — folk-psychology applies to the simulacrum not the simulator