are you using jev for llm-as-judge eval testing? seems like it would be a good
are you using jev for llm-as-judge eval testing? seems like it would be a good fit but here I am trying to fit a solution into a problem
Crawled from X, GitHub, blogs, and docs. Jev classifies, de-duplicates, and ranks. Every row links back to the original source.
Jev scores relevance and originality, then we mix in public traction.
are you using jev for llm-as-judge eval testing? seems like it would be a good fit but here I am trying to fit a solution into a problem
@JeremyLasne a bunch of people are using Jev to do this. check out the use cases. https://t.co/HQqOPGXJQ0
@JuanOwll @MitchellStooks @grok @TheMattBerman @peter51888206 @StealAds he’s not using Jev, idk why lie about this though
Using Jev to find relevant tickets for specific queries https://t.co/V4N0FVirZj
JevRouter vs. Jev API😲 https://t.co/cgR5rimKhJ https://t.co/YfDIJvOBka
@nurijanian you dont need to start with your own classifier and deal with the cold data start problem. you could end with a classic ML solution by using jev too
is anyone using jev with robotics rn and willing to vouch for it being useful?
@gregmushen @typesafeai "Greg’s strongest idea is using Jev for small, specific judgments that reduce your manual review. Priority uses: 1. Select the current result from nea
@DeRonin_ Smart move using Jev like that
Jev api key lazim acil hocam hadii ritim kaciyor
https://github.com/oxwen11/awesome-jev
https://github.com/typesafe-ai/typesafe-sdk-js
https://github.com/alterhq/typesafe-sdk-swift
https://github.com/AbdelStark/bicameral
https://github.com/Butochnikov/typesafe-sdk-php
https://github.com/codeitlikemiley/typesafe-sdk-rust
https://github.com/InsaneArts/typesafe-sdk-swift
https://github.com/aoprisan/typesafe-ai-scala-sdk
https://github.com/netf/typesafe-sdk-rs
https://github.com/deepanwadhwa/OpenDecision