Transformers are recurrent through autoregression because K/V stream provides horizontal information flow across positions.

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

• Transformers use an anti-Markovian solution that recomputes relevant numeric information at each step in the Multi-Object taskclaim0.792
  Prior finding from Grant et al. 2025 used to interpret low MAS IIA for GRU-Transformer hidden state comparisons.
• Different introspective tasks may preferentially use different path distributions in the transformer.claim0.791
  Interpretive claim connecting exponential path combinatorics to Lindsey's layer-dependent findings.
• Redundant information paths create interference patterns, so transformers likely experience memory and cognition as interferometric and continuous.claim0.785
  Janus's claim linking path redundancy to interferometric phenomenology.
• The problem isn't that it is a transformer. The problem is that it is an auto-regressive LLM. Auto-regressive LLMs that compute each token with a fixed number of computational steps can't reason, regardless of the details of the architecture.quote0.771
  LeCun's post on X supporting the view that fixed-step probabilistic prediction precludes consciousness in LLMs.
• R-Transformer: Recurrent Neural Network Enhanced Transformer (Wang et al., 2019)concept0.765
  Prior work on recurrently generated position encodings; cited as precedent for TEM-t's recurrent position encoding method.
• There are two types of phenomenal time: inter-frame discrete (~40 Hz) and intra-frame continuous drift; transformers have analogous dual temporality: within-token and inter-token.claim0.763
  Cube Flipper and Imago found convergent phenomenology between human meditation and transformer structure.
• autoregressive recurrenceconcept0.760
  Transformers are recurrent through autoregression because the K/V stream provides horizontal information flow across positions, even though each forward pass is feedforward.
• The direct path W_U W_E in larger transformers represents bigram statistics not captured by more general grammatical rulesclaim0.759
  Interpretation of the role of the direct path in multi-layer transformers; e.g. encoding that 'Barack' is often followed by 'Obama'