| name | elegance-trap-probe |
| description | Strategy: Attack a beautiful unified result on the suspicion that its beauty is the bug. Distinguishes EARNED simplicity (forbids/predicts/subsumes) from DECORATIVE simplicity (re-describes/relabels/accommodates). Directly serves the Occam aesthetic by making it a falsifiable bar, not a vibe. Methods: Sober parsimony-as-evidence, MDL, Meehl risky prediction, accommodation-vs-prediction. |
| type | strategy |
| produces | EleganceVerdict |
Elegance Trap Probe
The counter-intuitive attacker. Every other strategy attacks weaknesses; this one attacks a STRENGTH — the artifact's beauty. A common guiding aesthetic is Occam: a good result should be simple and elegant (LLM scaling laws replacing linguistics-inspired CNN/RNN; one principle of natural selection explaining all species). When we produce a beautiful unified result — one generator, a small number of projections, the key object as a symmetry — that is exactly what we hoped for. Which is precisely why it's dangerous. The same aesthetic that signals truth also seduces: a pretty story is easy to believe because it's pretty, not because it's right. This strategy interrogates whether the elegance was EARNED or is DECORATIVE, turning the aesthetic from a feeling into a falsifiable bar.
The distinction that does all the work
Earned simplicity buys its compression by FORBIDDING and PREDICTING more. Natural selection is elegant because it forbids vast swaths of observation (no species improves for its own sake; no inheritance of un-selected acquired traits at the population level) and predicts specifics (fossils in strata order, antibiotic resistance dynamics). Scaling laws are elegant because they PREDICT loss at unseen scale — risky, falsifiable, and they held. Earned simplicity is a compression of MANY constraints into ONE generator that then GENERATES those constraints back, plus new ones.
