larashero3-dotcom/lieflat-less-ai-tone
一个基于 283 万字语料统计的去 AI 味 skill · An AI-tone removal skill grounded in a 2.83-million-character corpus study
About the project
A skill for removing "AI tone" from Chinese text, grounded in a corpus study of 2.83 million characters that tested 26 features for distinguishing generated from human writing.
Useful for
- Check your own text for AI-tone markers with the check-structure and check-translationese scripts
- Recompute frequency metrics on your own corpus by swapping in your .md directories
- Consult RESEARCH.md to see which popular AI-tone markers failed statistical testing
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 30 stars so far today, about 43 expected by the end of the day.
- The repository is 29 days old and already has 1,794 stars.
- Top new repositories this month: #39.
- About 8 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 1,794
- Stars in a day
- 43
- Forks
- 119
- Issues and pull requests
- 3
- Watchers
- 3
- Language
- Python
- License
- MIT
- Created
- August 20, 2026
- Last push
- August 24, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 18, 2026Top new repositories this month: #37
- September 17, 2026Top new repositories this month: #38
- September 16, 2026Top new repositories this month: #45
- September 15, 2026Top new repositories this month: #87
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/larashero3-dotcom/lieflat-less-ai-tone)Similar projects
-
8.6
TheoLeeCJ/SemIf
An open reproduction of the Jev-style semantic decision interface: reads typed option probabilities directly from a 4B model's logits without generating text. Runs on a single RTX 3090.
-
7.1
vinnylarouge/jevlike
A small trainable model that picks one option from a changing list of text options in a single forward pass, an open alternative to TypeSafe's Jev. Aimed at developers who need fast classification or menu selection…
-
6.9
Continuum-AI-Corp/OrcaBonsai-27B-Uncensored
A tool for runtime refusal ablation in the compressed Ternary Bonsai 2 27B LLM: it projects the residual stream to remove the refusal direction without modifying or re-quantizing weights. Runs on Apple Silicon via MLX.
-
6.6
TianyuCodings/NanoJev
A nano replica of Jev built on Qwen3-0.6B that outputs probability distributions over candidates in a single forward pass with no token decoding, plus a training pipeline and game demos (maze, Snake).
-
6.3
zhengkid/Dream-RSI
Research project on recursive self-improvement: past discovery histories become a replay simulator used to evaluate and refine exploration policies. Code is still being prepared; paper and demo are available.
-
4.9
ekzhang/openjev-sglang
HTTP server implementing the TypeSafe/Jev API for structured text classification on Qwen3.6-35B-A3B via SGLang; returns answer probabilities without generating a chain of thought.