artifact
active
artifact:janus-information-flow-transformers-twitter-thread-sept-2025

Janus Information Flow Transformers (Twitter thread, Sept 2025)

Original thread by janus explaining transformer information highways and introspection capabilities, posted on X.

Neighborhood — ranked by edge-count

Thinkers (1)

thinker
  • Author of the thread on transformer information flow; researcher exploring AI and consciousness.

Frameworks (1)

framework
  • A framework from Wolfram physics viewing computation as a causal graph with foliations/time-slices specifying computation order.

Methods (1)

method
  • Caching of key-value pairs to avoid recomputation; also provides a mechanism for introspection of earlier computations.

Concepts (10)

concept
  • Proposed pathway flowing through layers at each position; calculates K/V values that feed horizontal information flow.
  • The ability of a model to observe its own past internal states or computations; claimed to be architecturally permitted by transformers.
  • Transformers are recurrent through autoregression because the K/V stream provides horizontal information flow across positions, even though each forward pass is feedforward.
  • Proposed pathway flowing across positions at each layer; carries key, value, and attention-weighted information horizontally.
  • Idea that redundant information paths create interference patterns, leading to memory and cognition experienced as interferometric and continuous.
  • The number of distinct paths information can travel from point A to B in a transformer is C(m+n, n), quickly exceeding the number of atoms in the universe.
  • Process using Q, K, V to compute a heat map over K and weighted sum of V.
  • In attention, key vectors that advertise 'where in the future should look here?'
  • In attention, query vectors that ask 'where in the past should I look?' given the current state.
  • In attention, value vectors that carry the information future positions should receive.

Claims (9)

claim

Questions (1)

question

Artifacts (1)

artifact
  • Antra/Imago dialogue (cube_flipper, April 2026) arguing transformers are recurrent; cited as evidence for introspection capability.