Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
shade-arena-jev-monitor
Evaluating TypeSafe's Jev as a fast monitor and action gate for agent sabotage in SHADE-Arena, compared with Gemini 2.5 Flash/Pro.
Project facts
- Relationship to Jev
- Research
- Evidence
- Documented
- Language
- Python
- License
- MIT
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-17
- GitHub stars
- 0
- Evidence checked
- 2026-09-24T08:40:10.508Z
- Metadata checked
- 2026-09-24T08:40:10.508Z
- Check status
- current
Stars measure the whole repository, including work unrelated to Jev.
Evidence and scope
Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.
| [`llms/typesafe_llm.py`] | Jev monitor provider (`jev-latest`): yes/no question → `100·P`, automatic chunking under the token limit |
Evidence commit: 9db4d741ecb8431e3da671f00d8dd7ae40dd2682
Discovered through: awesome-jev.
How we review →