Shanahan's role-play paper: describe LLMs with programs, not minds
gerardsans · x · 2026-09-23
Replying to the agent-consciousness debate, @gerardsans cites Murray Shanahan et al.'s paper "Role-Play with Large Language Models" (arXiv:2305.16367). It argues that as dialogue agents act increasingly human-like, we need high-level descriptions that avoid anthropomorphism: framing agent behavior as role-play lets us use folk-psychological terms without ascribing traits LLMs lack. The paper applies this to apparent deception and apparent self-awareness — use programs, not minds.
More from AGI Musings
- Reader finishes the 500-page Hanson-Yudkowsky AI-Foom Debate, picks Carl Shulman as the winner — zetalyrae · 2026-09-23
- Prediction: LLM skeptics will soon humbly recant and claim 'ethics before certainty' — RileyRalmuto · 2026-09-23
- antirez: AI is winner-take-all, and money itself will eventually disappear — antirez · 2026-09-23
- Friedman says it's time to cry wolf over AI, as critics urge treating AI as a new species, not a tool — zetalyrae · 2026-09-23
- Skeptic mocks AI doomers: everyone parroting the same doom loop works at the same place — viksit · 2026-09-23
- AI labs will keep frontier models for themselves and target problems worth more than tokens — jbarbier · 2026-09-23