LEM/experiments/worf
Snider f79eaabdce feat: WoRF — Word Radiance Field experiments
NeRF-inspired technique for learning relational dynamics of language.
Not what words mean, but how they behave together — rhythm, pacing,
punctuation patterns, style transitions.

v1: positional field over text (baseline, memorises)
v2: masked feature prediction (relational, actually works)

Trained on Wodehouse "My Man Jeeves" (public domain, Gutenberg).
All 11 style features are highly relational — the field learns that
Wodehouse's style is a tightly coupled system.

Key finding: style interpolation between narrative and dialogue
produces sensible predictions for unmeasured features, suggesting
the continuous field captures real structural patterns.

Co-Authored-By: Virgil <virgil@lethean.io>
2026-03-04 09:43:38 +00:00
..
pg-wood.txt feat: WoRF — Word Radiance Field experiments 2026-03-04 09:43:38 +00:00
v1_positional.py feat: WoRF — Word Radiance Field experiments 2026-03-04 09:43:38 +00:00
v2_relational.py feat: WoRF — Word Radiance Field experiments 2026-03-04 09:43:38 +00:00
worf-field-jeeves.json feat: WoRF — Word Radiance Field experiments 2026-03-04 09:43:38 +00:00
worf-v2-relations.json feat: WoRF — Word Radiance Field experiments 2026-03-04 09:43:38 +00:00