23:52
2026-09-23
github.com
artificial-intelligence
Jev deserves hype but not the type its getting
TypeSafe AI's rubric-conditioned classification model Jev scored 98.84% overall accuracy on the CT1-8 core classification tasks, beating Claude Haiku 4.5 (96.46%), Claude Sonnet 5 (96.18%) and the ope…