Jev fills the general-purpose classifier gap: labels in code, no extra LLM call

alexcovo_eth · x · 2026-09-19

A discussion about Jev, pitched as the missing general-purpose classifier. Responding to "classifiers always existed," the author concedes BERT, DeBERTa, GLiNER and fine-tuned heads were all specialized — changing labels meant another training run, and faking it with LLM JSON output was slow, expensive, and poorly calibrated.

Jev's pitch: labels defined in code, typed answers with confidence scores, no extra LLM call. The argument isn't that classification is new — it's that a classifier this intelligent, fast, and cheap is new.

Original post →

More from Models

Models channel →