concept
active
concept:internalized-visual-operationinternalized visual operation
The visual operation embedded inside a functional token, requiring no visual supervision.
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Describes the properties of the functional token.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Technique of building a fluid, three-dimensional vision by closing one's eyes, relying on words and feeling to avoid arbitrary graphical over-specification.
- Supervisory signals for visual outputs; functional tokens do not require it.
- Criterion requiring that causal influence of internal state on description be internal, not routed through sampled outputs; rules out pseudo-introspection via self-observation.
- Method used with Andre and Anna: standing on site with eyes closed, abandoning preconceptions, visualizing the most comfortable remembered place
- Execution of code or tools outside the main model, causing context-switching in agentic methods.
- Linda primitive that withdraws a tuple matching a template; blocks if no match.