Docs / source reviewed
Mimicry
Check personal voice and meaning during a rewrite loop
How this project uses Jev
- Input
- A user draft, personal writing samples and candidate revisions
- Jev decides
- Style alignment and preservation of the intended meaning
- Code executes
- A generative model proposes edits; code runs a bounded evaluation loop and shows diffs for the user to accept or reject
Evidence and limitations
Jev evaluates while a separate model writes. Drafts and reference samples go to configured services. The local development extension does not automatically publish X posts; style quality was not tested here.
This project has not been run independently here. Author-reported results are not independently verified results.