Reprogrammability

Ability to alter large-scale anatomical outcomes by changing bioelectric pattern memories without genomic editing; a software-like property.

Neighborhood — ranked by edge-count

concept

Bioelectricity
implements
Proposed 'cognitive glue' common to both neural and developmental collective intelligence; implemented by ion channels and electrical synapses.

cosine ≥ 0.65 · no typed edge

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

remappingconcept0.734
The process of reinterpreting and recontextualizing memory engrams for new bodies and environments.
Corrigibilityframework0.723
The property of an AI being safe to shut down or modify; discussed in context of GPT.
Similar to how a programmer might try to reverse engineer complicated binaries into human-readable source code.quote0.716
Load-bearing analogy defining the aspirational goal of mechanistic interpretability
Turing Machineconcept0.709
Theoretical construct establishing classical demarcation between machine and environment via input/output channels.
Computational Irreducibilityconcept0.708
Wolfram's principle: no shortcut to predict emergent properties without full simulation.
Multiple Realizabilityconcept0.705
Philosophical framework asserting same function can be implemented by very different systems; key to arguing sentience is substrate-independent.
Recognition of self-generated outputsconcept0.700
Ability to distinguish one's own outputs from those of other models or humans; related to prefill detection.
Complex, generated structure cannot be arrived at in any other way.quote0.699
Concise statement that underscores the necessity of the generated process for real complexity.