Re:OpenJev
by mukundesh on Friday September 18, 2026 @09:41AM
(#49754286)
I am not sure how this is JEV, but just a llm following the JEV api, as it is using standard LLMS. The main contribution of JEV is not the API but the model itself. Can someone please explain ?
[ Parent
| on HN ]
Re:OpenJev
by cmrdporcupine on Friday September 18, 2026 @10:23AM
(#49754845)
the models will come. or be fine tuned
Re:OpenJev
by deepsquirrelnet on Friday September 18, 2026 @01:34PM
(#49757611)
I'm not sure anybody but people inside the company know if the model itself is a contribution. There's no publication and no architectural details. There's no benchmarks or comparisons published. You can do all of the things they claim with an LLM, not that I think that's what they did.
Likely they have some encoder (eg ModernBERT) trained to do late interaction or latent states along the lines of ColBERT, Perceiver IO or poly-encoders.