GWT-4: State-dependent attention enabling sequential querying of modules for complex tasks

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

• GWT-2: Limited capacity workspace, entailing a bottleneck and a selective attention mechanismconcept0.805
  Indicator: workspace bottleneck with selective attention.
• GWT-1: Multiple specialised systems capable of operating in parallel (modules)concept0.799
  Indicator from GWT: existence of specialized parallel modules.
• GWT-3: Global broadcast: availability of information in the workspace to all modulesconcept0.759
  Indicator: global broadcast to all modules.
• Perceiver architecture is some way from being a full implementation of GWT.claim0.729
  Case study conclusion.
• Directing response attention to complement syntax and/or mental state verbs (MSV) yields no significant alterations in IIT estimates compared to entire stimulus analysis.finding0.729
  Suggests LLMs do not represent complement/MSV linguistic features in the same way as they are crucial for human ToM development.
• sequential reasoning tasksconcept0.727
  Language model reasoning tasks with sequential geometry used in experiments.
• Any system monitoring and controlling its own processing requires all three hierarchical levels: perception, attention, meta-awareness.claim0.726
  Design principle with implications for AI and consciousness-UX; architectural requirement for self-directed cognition.
• Task instructions can be transcribed into prior beliefs of a generative model, making instruction-following an instance of prior belief specification.claim0.724
  Practical implication showing task instructions are equivalent to inducing prior beliefs in experimental settings