Local alternative
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.
Details →★ 21,612
jev-deferred-crispification
Position paper: the Hidden-Markov and fuzzy primitives missing from TypeSafe AI's Jev and System-One decision models. Two lemmas, one principle (Deferred Crispification), one architecture (BSF-S1).
Project facts
- Relationship to Jev
- Research
- Evidence
- Documented
- Language
- TeX
- License
- Not reported; check the repository
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-16
- 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.
> **30-second version.** TypeSafe AI's **Jev** (15 Sept 2026) launched the *System-One* class: no text, just typed probabilistic decisions (`Choice`, `Score`, `Noul`), calibrated via RLCD, at 70–500 ms and $0.042/1M tokens. Brilliant interface. Two missing primitives: **(1)** no Hidden-Markov belief over latent regimes, **(2)** no fuzzy membership for borderline predicates. We prove what breaks when you compose such heads in a pipeline (**Lemma 1**: calibration does not compose; **Lemma 2**: cli
Evidence commit: 9e6fd6435baa4bbe674ce2c1eb5ceba1310147a0
Discovered through: awesome-jev.
How we review →