devwithjev
— reading now— views
Submit a build

Jev Fine-Tuning for Local Classification

The author says Jev’s encoder can be fine-tuned into a faster, local classifier. The post does not describe a completed classifier build.

View on X
search foundersearch founder@n0riskn0r3ward𝕏
There's a fun mix of excitement and cope on my timeline re-Jev: - OMG I made Jev a year ago this is dumb - You can fine tune this encoder into a better, faster, local classifier, etc Re the "just train your own small classifier" crew - Voyage trains great, SOTA pointwise rerankers that are obviously specialized to the reranking task and have been at it for years, likely also using a strong synthetic data recipe... Exact setup in the response tweet. Do note that using Jev is definitely more expensive than using Voyage rerank-3 bc of the tokens in the lengthy rubric included in every request (t
Sep 20, 2026X postsView on X
The author compares this idea with Voyage’s specialized pointwise rerankers, noting that Jev requests include tokens from a lengthy rubric. They say using Jev is more expensive than Voyage rerank-3.

Also filed under Triage & routing

  • How to Build Things with Jev & OpenJevs

    How to Build Things with Jev & OpenJevs In this video, we build a model router using both the API-based original Jev and also using Semif. ‍ Github: code will be up in ...

  • Jev is HERE. How to use it

    Jev is HERE. How to use it In this episode, I talk with Ryan Vogel about Jev, a new type of AI built for classification. Ryan shows how Jev takes an input plus ...

  • Jev-Powered Agent Runtime for JarvisCore

    Muyukani Kizito says JarvisCore uses Jev in its agent runtime for RAG classification and ranking, model routing, subagent routing, and agent decisions.

  • Jev Benchmarks for Review Pipelines

    Niels Bantilan benchmarked Jev against a “System 2” approach for customer support, code review, and legal contract review. He reports Jev was up to x2.6 faster and at least x10 cheaper, with no loss in quality.