mini-Jev · read the letter What a Jev-style interface looks like on a frozen model: classify against a schema that arrives with the request by reading next-token logits, not by generating JSON. Measured on Qwen3-4B. TypeSafe's Jev is trained for typed decisions without open generation. mini-Jev asks how much of that interface an ordinary frozen model already provides, and measures it against today's path, grammar-constrained JSON. A JSON schema arrives with the request. Today the model writes a JSON object under a grammar, token by token.
| Stars | 59 |
| Forks | 5 |
| Language | Python |
| Category | AI Tool |
| License | MIT |
| Quality Score | 56.5595116308614/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-18 |
| Created | 2026-09-17 |
| Platforms | python |
| Est. Tokens | ~16k |
These tools work well together with mini-jev for enhanced workflows:
Explore other popular ai tool tools:
mini-jev is mini-Jev: what a Jev-style typed-decision interface looks like on a frozen Qwen3-4B — read the option letter's logits instead of generating JSON. Preregistered experiment, results, teaching bench.. It is categorized as a AI Tool with 59 GitHub stars.
mini-jev is primarily written in Python.
You can find installation instructions and usage details in the mini-jev GitHub repository at github.com/r-ms/mini-jev. The project has 59 stars and 5 forks, indicating an active community.
mini-jev is released under the MIT license, making it free to use and modify according to the license terms.