Redundant information paths create interference patterns, so transformers likely experience memory and cognition as interferometric and continuous.

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

• Transformer cognition operates via interference patterns across redundant paths, encoding nuanced state deltas similar to continuous human memory.claim0.848
  Proposes transformers experience cognition as interference-based and continuous; connects to Anima Labs reports of parallel processing.
• Different introspective tasks may preferentially use different path distributions in the transformer.claim0.798
  Interpretive claim connecting exponential path combinatorics to Lindsey's layer-dependent findings.
• So at any point in the network, the transformer not only receives information from its past... but also has causal influence over its future processing. So, saying that LLMs cannot introspect... is incorrect.quote0.797
  Core summary of Janus' position on autoregressive recurrence enabling introspection.
• probably helps not only with faithful reconstruction but also creates interference patterns that encode nuanced information about the deltas and convergences between states.quote0.786
  Key quote connecting path redundancy to interferometric information encoding.
• Transformers are recurrent through autoregression because K/V stream provides horizontal information flow across positions.claim0.785
  Claim formalizing the Anima Labs idea that transformers are effectively recurrent due to K/V stream.
• Transformers almost surely maintain input-injectivity throughout training, not just at initialisationhypothesis0.776
  Conjecture supported by Nikolaou et al. 2025 for last-token hidden states
• Transformers use an anti-Markovian solution that recomputes relevant numeric information at each step in the Multi-Object taskclaim0.767
  Prior finding from Grant et al. 2025 used to interpret low MAS IIA for GRU-Transformer hidden state comparisons.
• Transformers develop self-models through in-context learning, not just training data; even old base models without LLM-related text can bootstrap self-referential reasoning at runtime.claim0.764
  Antra's foundational claim about how introspection arises computationally rather than from memorised text.