jev-lm
y0usaf
A word-level generation experiment that asks Jev to select words or verify locally drafted continuations.
- License
- MIT
- GitHub Stars
- 5
- Source reviewed
- 2026-09-19
Where Jev makes a decision
Choice selects the next word; Noul evaluates candidate chunks and stopping conditions.
What this project offers
Exposes the limitations of using a decision model as a text generator.
Review scope
A research prototype whose reported small-vocabulary evaluation did not beat a unigram baseline; not a general language-model replacement or independently retested here.
Sources and implementation
Related projects
jev-review
NiazMorshed2007 · Evaluation & Observability
A local MCP code-quality reviewer returning structured scores to coding Agents.
jev-benchmarks
AbdelStark · Evaluation & Observability
A benchmark comparing Jev and GLiNER on text classification, probability calibration and selective automation.
jev-playground
mizchi · Evaluation & Observability
A MoonBit and TypeScript Jev playground covering games, browsers, command risk and small languages.
jev-chat
adhyaay-karnwal · Evaluation & Observability
A research chat decoder that repeatedly asks Jev to choose words or phrases and assembles them in code.