Small decisions. Interesting possibilities.Submit contentSubmit
Lieflat: Less AI Tone preview

Lieflat: Less AI Tone

A Chinese-language editing skill that removes AI writing tells, built on a corpus study that used Jev for roughly 500,000 semantic judgments.

Added to Jevfast

How it uses Jev

The corpus study behind the skill used Jev for its semantic layer: passage-level candidates were turned into closed label questions, such as how many times a paragraph renames one entity, whether an adjacent sentence pair is merely continued or jumps, and whether a colon announces a conclusion. The study reports about 500,000 such judgments across its two rounds, and the skill's published runtime does script checks plus session-model review.

What Jev decides

Research labelling protocol (illustrative)Example answers · not a recorded Jev response · Source ↗
Question 1 · rename groups
YOUR APP
INSTRUCTION

How many times does the paragraph rename one entity or concept with a different content word instead of repeating the same name?

STATE

The study's semantic layer gives each candidate one closed label from the criteria file: a paragraph for the renaming count, a sentence pair for the transition type, a colon sentence for its category, or a three-sentence group for structural repetition. The chart shows the renaming question, the strongest signal in the study.

JEV · CHOICE
  1. 0组
  2. 1组
  3. 2组
  4. 3组及以上
  5. 无法判断

App workflow

  1. Run the script check

    A local script counts punctuation, sentence lengths and section shapes, and grades each hit for the report.

  2. Extract semantic candidates

    The script exports paragraphs, sentence pairs, colon sentences and three-sentence groups for the semantic layer.

  3. Judge each candidate

    Each candidate is given one closed label from the criteria file, with a confidence and a one-line reason.

  4. Report before editing

    The skill delivers the measured counts, examples and proposed edits, and waits for the writer's reply.

  5. Rewrite and retest

    After approval it applies the agreed edits, reruns the checks and produces a before-and-after report.

Why it is interesting

It measures AI writing tells against 629 human-written controls and a paired retest, then drops rules that the retest contradicted instead of keeping a longer checklist. The paper trail keeps raw hit counts and per-item labels so a claim can be recounted.