A formal model fails to convey the essential meaning of a concept because it treats all behaviors equally and does not distinguish motivating behaviors.

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

• In order to actually do anything, the model must act through simulation of something.claim0.797
  Key consequence: GPT's power comes from simulating something contingent.
• Models more effective at recognizing abstract nouns than other concept typesfinding0.784
  Opus 4.1 demonstrates highest introspective awareness on abstract nouns (justice, peace, betrayal) with nonzero awareness across all concept categories tested.
• This theory doesn't have to correspond exactly to human behavior or social customs; we only need analogs useful for program correctness.claim0.783
  The speech act theory for programming can be simpler than human models.
• In some sense, this is the simplest language model we profoundly don't understand. And so it makes a natural target for our paper.quote0.782
  Articulates why a one-layer transformer with MLP is the appropriate starting target for mechanistic interpretability
• The strengths of all three models (concurrent OOP, logic, functional) are irrelevant to parallelism, and generally unhelpful in dealing with process creation and coordination.claim0.777
  Assertion that the popular models add nothing to parallel programming.
• Models that are competent all represent data in a similar way; all strong models are alike, each weak model is weak in its own wayclaim0.776
  Author's interpretation of the VTAB alignment results echoing Tolstoy
• Models are not merely tracking dialogue context features; same-concept steering shows privileged internal access is necessary to explain self-report shiftsclaim0.775
  Addresses skeptical alternative that reports reflect only conversational content
• Object models in which time, versioning, causality, etc., are significant are probably far better modelled by considering the time component as another key rather than an intrinsic property of the underlying model.claim0.775
  Claim that orthogonal dimensions like time should be explicit keys in the associative model.