concept
active
concept:simulators-frameworkSimulators framework
The view that pretrained LLMs are best understood as simulators capable of generating context-appropriate characters rather than single agents
Neighborhood — ranked by edge-count
Papers (1)
paper
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 underlying LLM with autoregressive sampling; a passive entity capable of generating an infinity of simulacra but lacking its own beliefs or goals
- 1984 Ashton-Tate integrated system with frames, FRED language, and overlapping windows; design reference for Playground's approach.
- The framework proposed: self-supervised models are simulators that generate simulacra; distinguishes simulator from simulated agents.
- Mechanistic interpretability framework for understanding neural network computation as circuits of features
- Bostrom's category of AIs that perform specific tasks without overarching goals.
- A systematic framework for analyzing and comparing programming systems along multiple independent axes, proposed as a common language for programming systems research.