Using Jev as an evaluation layer for everyday work
The author is building an evaluation framework with Jev so routine output is checked automatically, cutting token spend and time spent babysitting sessions.
Finally got to using Jev today. The most immediate use case I'm trying out is using Jev as an evaluator layer for the work I do regularly. I think everyone knows the pains of going back and forth manually with AI models which inflates token spend and wastes time at the end of the day. If you can create a solid evaluation framework and have things loop through Jev, you could feasibly get much further at a lower cost without having to babysit sessions. Very excited for this one.
This post quotes another post: “ChatGPT co-inventor releases Jev, a model built for decisions rather than text”