Trending storyPast story
Jevper: A Jev-shaped classification wrapper for any OpenAI-compatible model
1 report1 sourceupdated 6 days ago
What happened
Summary
Jevper 是一个轻量封装，让任何兼容 OpenAI 接口的模型输出分类概率和置信度分数，而不是直接吐文字。它复刻了 Jev 的“TypeSafe System One”接口，把生成模型当分类器用。项目没给基准测试或生产案例，但思路很直接：用概率做决策，而不是靠模型自己写答案。如果你需要模型在几个固定类别里做选择，并且想知道它有多确定，这个工具能省掉...
Coverage
Follow the reports to see the story from different sides.
Sep 23
- Hacker News front pageJevper: A Jev-shaped classification wrapper for any OpenAI-compatible model
Jevper is a lightweight wrapper that lets any OpenAI-compatible model output classification probabilities and confidence scores instead of raw text. It replicates Jev's "TypeSafe System One" interface for deterministic classification. The post doesn't include benchmarks or production use cases, but the idea is straightforward: use generative models as classifiers with probability-based decisions.