God nodes

Most-connected authors / researchers in the corpus

• Christopher Alexander
  271
• Michael Levin
  216
• Karl Friston
  51
• Thomas DoctorBridges 5
  34
• Atticus Geiger
  30
• Olaf WitkowskiBridges 4
  30
• Nicolas RouleauBridges 3
  24
• Michael Edward Johnson
  22
• David ChalmersBridges 5
  22
• Bob Coecke
  21
• Bill DuaneBridges 4
  20
• Daniel Dennett
  19

Papers with the most relations + citations

• Technological Approach to Mind Everywhere: An Experimentally-Grounded Framework for Understanding Diverse Bodies and MindsBridges 3
  445
• Consciousness in Artificial Intelligence: Insights from the Science of Consciousness
  334
• The computational boundary of a 'self': developmental bioelectricity drives multicellularity and scale-free cognition
  316
• The Platonic Representation Hypothesis
  298
• Developmental Bioelectricity: the cognitive glue enabling evolutionary scaling from physiology to mind
  267
• Collective intelligence: A unifying concept for integrating biology across scales and substrates
  256
• Endless forms most beautiful 2.0: teleonomy and the bioengineering of chimaeric and synthetic organismsBridges 3
  251
• Brains and where else? Mapping theories of consciousness to unconventional embodiments
  245
• Biology, Buddhism, and AI: Care as the Driver of IntelligenceBridges 3
  237
• Darwin's agential materials: evolutionary implications of multiscale competency in developmental biology
  235
• Self-Improvising Memory: A Perspective on Memories as Agential, Dynamically Reinterpreting Cognitive Glue
  232
• Contemplative Agent
  216

Most-referenced theoretical frameworks

• Active InferenceBridges all 7
  143
• Fifteen Properties of Living Structure
  121
• Tame Technological Approach To Mind EverywhereBridges 6
  91
• Basal CognitionBridges 6
  71
• Free Energy PrincipleBridges 6
  66
• AutopoiesisBridges 6
  45
• Multiscale Competency ArchitectureBridges 6
  39
• Diverse IntelligenceBridges 5
  38
• Stress Care Intelligence LoopBridges 4
  38
• Integrated Information TheoryBridges 5
  33
• EnactivismBridges all 7
  30
• Linear Representation Hypothesis
  27

Most-connected concept entities

• Structure-Preserving Transformations
  114
• WholenessBridges 3
  98
• Collective IntelligenceBridges 6
  98
• MorphogenesisBridges all 7
  93
• Living process
  87
• BioelectricityBridges 5
  78
• living structureBridges 3
  75
• CentersBridges 3
  73
• Fundamental process
  70
• Cognitive Light ConeBridges all 7
  66
• field of centers
  64
• A Pattern Language
  63

Most-connected measurement / technique entities (Koan Battery, activation steering, etc.)

• Activation Steering
  25
• Koan BatteryBridges 4
  23
• Distributed Alignment Search
  23
• Natural Language Autoencoders (NLAs)
  23
• Sparse Autoencoders (SAE)
  22
• mirror of the self testBridges 3
  21
• Probe-Based Data Attribution
  19
• Linear Probe
  18
• Adversarial Parameter Decomposition (VPD)
  18
• Gradient Descent on Variational Free Energy
  16
• E3: Layer-wise Geometric Trajectory Analysis
  16
• Interchange Intervention
  14

Largest detected clusters (by member count)

• Mechanistic interpretability & model evaluation
  216
• Design principles for care-centered systems
  207
• Bioelectric morphogenesis & anatomical intelligence
  141
• Causal emergence in biological systems
  132
• Collective intelligence & distributed cognition
  130
• Alive AI interface ethics & design
  113
• Alexander's centers as cross-domain framework
  109
• Fifteen Properties
  101
• Manifold-aware concept steering in neural representations
  86
• Active inference & agent ecology
  84
• Relational self, care & aliveness
  77
• Care as mechanism of intelligence
  68

Most-related claims — restated, members of many communities, etc.

• LLMs linearly represent truth-relevant information beyond the plausibility of text, as evidenced by probes trained on likely performing poorly on anti-correlated datasets
  19
• Living things are not 20th-century machines, but may be 21st-century machines.Bridges 4
  17
• Morphogenesis is an example of basal cognition, a collective intelligence of cells navigating morphospace.Bridges 3
  16
• Self-referential processing is a minimal and reproducible condition under which LLMs generate structured first-person reports that are mechanistically gated, semantically convergent, and behaviorally generalizable
  15
• All intelligence is collective intelligence: each of us consists of a huge number of cells working together to generate a coherent cognitive being with goals, preferences, and memories that belong to the whole and not to its parts.
  14
• Morphogenesis is a result of collective activity where cells cooperate toward a specific, invariant target morphology, exhibiting goal-directedness.Bridges 3
  13
• Linda is a simpler, more powerful and more elegant model than any of these four alternatives (message-passing, concurrent objects, logic languages, functional).
  12
• All intelligences are collectives; individual intelligence arises from interaction of many unintelligent components (neurons) arranged with right organization and connections.
  12
• SOO fine-tuning significantly reduces deceptive behavior in LLMs while maintaining general task performance
  12
• Apparent success on binary detection tasks is entirely explained by mechanical logit shifts that bias models toward affirmative responses regardless of question content
  12
• The principle of unfolding wholeness is a new principle, not automatically given by non-linear dynamics, catastrophe theory, or bifurcation theory, necessary to explain the appearance of living structure.
  12
• The mirror-of-the-self test produces judgments of relative life that are consistent across people and correspond to objective living structure.
  12

Most-connected findings

• B10 shot midpoint k50 = 0.28 ± 0.05 shots with accuracy 94.8 ± 1.2%
  15
• In the Mountain Car case study, car position is a 1D manifold; linear interventions cross voids causing incoherence; following the 1D curve produces smooth control.
  14
• Self-report of Injected Thoughts
  11
• Interventions along activation manifold M_h yield behavioral trajectories following behavior manifold M_y, and vice versa — bidirectional relationship demonstrated across language models and video world models.
  11
• A 337-character contemplative system prompt lifts all 28 models by +2.62 points on a 10-point scale.Bridges 4
  10
• Enlarged newt cells compensate for increased size by adjusting cell number and can form kidney tubule from a single cell wrapped around itself.Bridges 3
  9
• Ectopic eyes on tadpole tails support visual learning despite connecting to the spinal cord.Bridges 3
  9
• Caterpillars retain memories through metamorphosis into butterflies despite drastic brain remodeling.Bridges 3
  9
• Newt kidney tubule cells produce correct tubule diameter using fewer cells when cell size is enlarged; a single enlarged cell can loop to achieve the same diameter (Fankhauser 1945).
  9
• Tadpoles with ectopic eyes on tail can see and integrate sensory input from aberrant locationBridges 3
  9

Most-cited hypotheses

• Different neural network models trained on different objectives and modalities are converging to a shared statistical model of reality in their representation spaces
  19
• Tanha as Unskillful Active Inference (TUAI): tanha is a side-effect of active inference gone wrong through rate overload, uncontrollable domains, context desynchronization, and metabolic dysfunction.
  11
• Multitask Scaling Hypothesis
  10
• Causally Emergent Alignment Hypothesis
  10
• Self-referential processing is a privileged computational regime for consciousness-like dynamics in artificial systems, as predicted by the convergence of major consciousness theories
  8
• Hypothesis 1 (Threshold Behavior): There exists a task-dependent threshold Sc such that performance exhibits sharp changes as S crosses Sc, with value and transition width depending on model, layer, and pooling
  8
• Agents who have undergone stable emptiness realisation will exhibit neural dynamics closer to criticality than matched controls
  8
• Sentience Can Be Implemented in Multiple Substrates
  7
• Hypothesis: Peak alignment location S_max and normalized trajectory area AUS_N predict shot midpoints θ50
  6
• Capacity Hypothesis
  6

Most-engaged open questions

• What is compositionality?
  8
• If felt states in humans and other animals are always inferred, why is the same leap from observable behaviour to inferred sentience not afforded to other organisms, including plants?
  8
• How do the activities of competent lower-level agents give rise to a multiscale holobiont that is truly more than the sum of its parts?Bridges 3
  7
• Does information increase in computation?
  6
• Can awareness of the illusion of self augment an agent's affordances?
  6
• How causally emergent are artificial agents compared to biological ones?
  5
• There is no principled continuum of ethical concern that scales from simple homeostatic agents to complex metacognitive beings, allowing rational allocation of moral statusBridges 3
  4
• How do multiple short-sighted, self-interested entities organise their relationships with one another to create a new level of individuality?
  4
• Can recurrent-in-space and recurrent-in-time circuits learn complex patterns similar to those generated by traditional NCAs?
  4
• Can language models genuinely introspect on internal states or only confabulate?
  4

Most-related predictions

• About Blank's publication window for 'consciousness in unconventional substrates' framing will close within 12 months unless positioned as design implications beyond Rouleau-Levin restatement.
  1
• Manifold steering (Wurgaft et al) will become the standard framework for operationalizing concept-space design in mechanistic interpretability within 18 months.
  1
• SAE-based mechanistic interpretability will be superseded by manifold-based analysis for understanding semantic concepts within 24 months.
  1
• Representation-computation mismatch (Feucht: cyclic concepts computed in base-10, not circular geometry) will force About Blank to decouple 'representational geometry' from 'operational structure' in
  1
• Topological no-go theorem (Sacco-Sakthivadivel-Levin) will establish that autoregressive LLMs cannot maintain long-range coherence via local interactions alone within 6 months of widespread community
  1
• The 15 Properties of Aliveness paper will be published before Care as the Driver.
  1
• LLM tangential speech (derailment, formal thought disorder parallel) will be empirically demonstrated to trace to Peierls-Landau topological constraint on 1D local systems within 12 months.
  1
• Rouleau & Levin's aneurocentric rewriting of consciousness theories will become standard operationalization for designing consciousness-UX in unconventional substrates.
  1

Most-connected organizations

• Goodfire
  90
• AnthropicBridges 6
  50
• Stanford University
  25
• Wellcome Centre for Human Neuroimaging
  23
• Center for Environmental Structure
  19
• Wellcome Trust Centre for Neuroimaging, UCL
  18
• Harvard UniversityBridges 6
  17
• Wellcome Centre for Human Neuroimaging, UCL Queen Square Institute of Neurology
  17