Open questions on JEV: model size, calibration reliability, and a future fine-tuning API

vykthur · x · 2026-09-20

Calling JEV exciting for evals and automated agent optimization, vykthur raises three open questions: how large the model is and whether it's built on a pretrained LM base; beyond early third-party tests, how well calibrated it is and where that breaks down; and whether weak areas can be addressed — even if not now, via some future fine-tuning API.

Original post →

More from coding & agent

coding & agent channel →