concept
active
concept:superposition-of-simulacraSuperposition of Simulacra
The state in which a dialogue agent maintains multiple possible characters simultaneously, refined as the conversation proceeds
Neighborhood — ranked by edge-count
Frameworks (1)
framework
- Simulacra in Superposition Frameworkassociated_withThe more nuanced second metaphor: LLM as simulator maintaining a superposition of possible simulacra across a multiverse of characters
Concepts (2)
concept
- Simulacrarelated_toThe phenomena simulated by a simulator, such as agents or processes that appear in text generated by GPT.
- Multiverse of Possible Charactersassociated_withThe branching tree of possible token continuations, each branch representing a distinct narrative path or character
Quotes (1)
quote
- GPT-4 ChatGPT's own articulation of the ambiguity of its self-reference, directly illustrating the paper's superposition of selfhood theories
Hypotheses (1)
hypothesis
- Conditional prediction about how a well-informed dialogue agent would handle questions of personal identity
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.
- Phenomenon where models represent more features than dimensions via almost-orthogonal directions.
- A false copy that lacks the depth and authenticity of the real, morphogenetically produced thing.
- Specific phrases or sequences memorized via binary features in superposition, enabling narrow pattern matching despite few neurons
- The phenomenon where the residual stream communicates many more features than its dimensionality by encoding information across overlapping subspaces
- Core theoretical framework: neural networks represent more features than neurons by encoding features as directions in superposition
- The notion that a sufficiently accurate simulation of consciousness could cross into authentic consciousness.
- Theoretical model of how neural networks encode more features than dimensions, informing linear representation work.
- Interpretation of the cars-in-superposition circuit finding as an intentional representational strategy