Carrier / Notation Lab
From correct recovery to artistic expression: a new Carrier comparison
News / An artistic comparison
Carrier’s new expression study asks what a work opens for its creator and its viewer—not only whether its structure survives.
The release contains two distinct rounds. The first gave nine fresh readers the same philosophical matrix through a Carrier image, structured JSON or controlled English. All nine answered the sixteen fixed factual probes correctly and produced valid Carrier replies. Every reader used a common semantic adapter, so those results do not isolate a notation advantage. The first qualitative rubric also reached a ceiling.
Lucid then sharpened the question: an art test should address the depth and quality of expression, and the room for love and freedom that a medium offers. A separate exploratory protocol was frozen before new native works were made.
Six creator–viewer pairs were planned across two themes: care without possession, and common life without coerced agreement. Creators received Carrier, free-form JSON or prose; viewers could choose any of those media, or meaningful refusal, for their response. Of six fixed planned encounters, 4 source works and 4 answering works are available.
The completed viewers exercised their response choices as follows: prose 4. Those choices are self-selected observations under this workflow, not evidence of a general preference or artistic superiority.
The public gallery includes the available works, interpretations, replies, process records and separate artistic judgments. The rubric asks for concrete evidence and counterreadings across six dimensions. It does not reward agreement, warmth or length on their own.
Two fresh appraisers supplied evidence and counterreadings. They differed on five judgments, while both concentrated on the upper two categories. The release preserves those disagreements and the ceiling; it does not turn them into a winning medium.
This remains a small, uneven exploratory sample. The source works, creators, viewers and native affordances differ, and provider-capacity interruptions are retained as unavailable. It does not establish a causal ranking of media or a validated measure of love. It makes the artistic question—and the actual encounters—available for inspection.
Enter the art-first galleryMatched-input galleryFresh viewer collectionArt-first study record