devwithjevJev Judges Pages Against Questions
Asif used Jev, from TypeSafe, to judge pages against lists of questions, returning a yes, no, or score with a probability for each. He says 25 judgments about a page take about a third of a second.
Asif@akbuilds_๐
I asked an AI 52,350 questions. It cost 41 cents. The model is Jev, from TypeSafe. It doesn't write text. It judges. You give it a page and a list of questions, and it sends back a yes, a no or a score for each one, with a probability. 25 judgments about a page take about a third of a second. At that price you stop sampling and judge everything. So I judged every page ChatGPT, Claude, Gemini and P
Asif says the low cost led him to stop sampling and judge every page.
Also filed under Research & data
- Visualizes French Wikipedia Elites
The project is a data visualization of French elites on Wikipedia. Its crawl is ongoing, with new biographies arriving.
- GraphRAG with Swappable Laya and Jev Models
This project is an agentic GraphRAG pipeline with swappable local Laya or cloud Jev decision models.
- Jev Probability Calibration Experiments
The repository presents reproducible experiments on Jev probability calibration, uncertainty, and forecast preservation.
- Benchmarks Jev for Malicious Skill Detection
jev-skillbench benchmarks Jev as a malicious agent-skill detector on MalSkillBench with verify-and-escalate evaluation.