"Jev isn't an LLM" debate: BERT-family are language models too, zero-shot classifiers underrated

RexDouglass · x · 2026-09-20

A debate over the new Jev model's positioning broke out on X. Quoting "Jev isn't an LLM," MaziyarPanahi notes that BERT, DeBERTa, and ModernBERT are all language models — many people conflate "LLM" with "language model/transformer." mert bozkir quips that anyone comparing Jev against GPT-5.6 has never fine-tuned BERTForXYZ for a living, and adds that zero-shot classifiers never got scaled the way decoder-only models did: many problems solved with LLMs could have been solved with them — "a skill issue."

Original post →

More from Models

Models channel →