10

warp the surface / machine language

semantic gravity

create / explore / learn / play

Words look independent until a local embedding model turns their relationships into forces. Meaning does not label the field; it changes how every body is allowed to settle inside it.

Enable local semantics, add a word or short phrase, then disturb the field. Similarity becomes attraction distance, while the whole set determines what counts as near or far.

local semantics / offindependent terms

enable the field · add one idea · watch every other relationship move

Six terms are present, but the page has not asked a model how they relate.

English-first local embeddings · maximum 12 bodies · your terms are not stored

bodies6
nearestunknown
selectednone
modelall-MiniLM-L6-v2

Semantic inference is optional and runs in this browser. Enabling it downloads an Apache-2.0 embedding model from Hugging Face: about 30 MB on the preferred WebGPU path and about 55 MB on the quantized WASM fallback. Typed concepts are sent only to the local worker and are never written to Warp experience memory.

felt

Adding one concept changed the motion and resting distance of terms you never touched. Even apparently opposed words could remain close because the model learned contextual similarity rather than human agreement.

found

An embedding does not contain a final map of meaning. It places language in a high-dimensional relational space; this experience turns those relative distances into temporary physical constraints.

carry

Search, recommendations, clustering, retrieval, and AI memory all make consequential decisions from representations of nearness. A similarity score becomes more legible when you can feel what it pulls together.