concept
active
concept:simulacraSimulacra
The phenomena simulated by a simulator, such as agents or processes that appear in text generated by GPT.
Neighborhood — ranked by edge-count
Thinkers (1)
thinker
- Janus (author)studiesThe author of the LessWrong post 'Simulators'.
Claims (1)
claim
- Clarifies where agency resides.
Concepts (2)
concept
- simulacrumrelated_toA false copy that lacks the depth and authenticity of the real, morphogenetically produced thing.
- Superposition of Simulacrarelated_toThe state in which a dialogue agent maintains multiple possible characters simultaneously, refined as the conversation proceeds
Artifacts (1)
artifact
- Simulators (LessWrong post)introducesThe paper being extracted.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- The more nuanced second metaphor: LLM as simulator maintaining a superposition of possible simulacra across a multiverse of characters
- The notion that a sufficiently accurate simulation of consciousness could cross into authentic consciousness.
- The ontological separation between the generative rule (simulator) and the instances it produces (simulacra).
- Explains how role-played agency can have real-world consequences even without underlying genuine agency
- Paper on LLM-based simulacra of human behaviour; cited as ref 3
- The underlying LLM with autoregressive sampling; a passive entity capable of generating an infinity of simulacra but lacking its own beliefs or goals
- Contrastive sentence embedding method used in color cooccurrence experiment; represents contrastive language learner
- Self-supervised contrastive learning method cited as instance of NCE-type objectives that converge to PMI kernel