Rudimentary language models are challenged by long sequences of outputs.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Multiscale systems like those prevalent in biology are capable of organizing into complex patterns, whereas rudimentary language models are challenged by long sequences of outputs.claim0.839
  Conclusion about why biology organizes complexity well and flat LLMs do not
• language models recapitulate cyclic structure of human concepts from pretraining datahypothesis0.806
  Explanation for why manifold geometry emerges: implicit structure in training data (co-occurrence patterns) shapes internal representations.
• The inability for autoregressive large language models to maintain states of long-range order resembles tangential speech or derailment in formal thought disorder.claim0.786
  Analogy between LLM incoherence and schizophrenia symptoms
• It's tricky, because for a typical language model the entity is sort of tricameral: the base simulator, the simulated simulator, and the simulated awareness.quote0.777
  Antra's earlier definitive statement of the tricameral model.
• Language models are few-shot learners (Brown et al., 2020)concept0.775
  Demonstrated transformers on mathematical understanding and logic; cited to motivate transformer versatility.
• In some sense, this is the simplest language model we profoundly don't understand. And so it makes a natural target for our paper.quote0.772
  Articulates why a one-layer transformer with MLP is the appropriate starting target for mechanistic interpretability
• "The model is based on generative communication. If two processes need to communicate, they don't exchange messages or share a variable; instead, the data producing process generates a new data object (called a tuple) and sets it adrift in a region called tuple space."concept0.771
• Models might produce first-person experiential language by drawing on human-authored self-descriptions in pretraining data without internally encoding these acts as roleplayhypothesis0.769
  Alternative hypothesis for how experience reports arise without explicit performance