Jeeves. Reasoning improves Jev-like decision models

Re:Jeeves. Reasoning improves Jev-like decision models by zihotki on Tuesday September 29, 2026 @11:03AM (#49894558)

There are two parts in the data you supply to Jev for classification - the prompt describing your classification and the data. The data can be quite small - a simple chat message. And prompt part could be considerable since you need to describe your rubrics well.

With Jev you each time pay for your prompt, you can't cache it.

[ Parent | on HN ]

Re:Jeeves. Reasoning improves Jev-like decision models by sarkarghya on Tuesday September 29, 2026 @01:02PM (#49896512)

I mean, it sounds like it's only ideal for cases with significant system prompt overhead. I don't think Jev was built to have a large well described prompt setup. To me its more like a happy go lucky small label classification tool with important decisions left to stronger agentic models or yk humans.

[ Parent | on HN ]