"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."
More from Models
- 100-run trolley problem test: Jev pulls the lever 99% of the time — FinanceYF5 · 2026-09-20
- Parallel-sampling decision model Jev routes in ~1s vs 4-14s for regular LLMs — TigerOk4538 · 2026-09-20
- Working memory seems to scale with model size, according to one researcher's observations — repligate · 2026-09-20
- Burkov disputes Stanford AI Index: does the US really lead with 59 notable models? — burkov · 2026-09-20
- JEV watch: a model that returns typed probability decisions instead of text — sven_ai · 2026-09-20
- Open questions on JEV: model size, calibration reliability, and a future fine-tuning API — vykthur · 2026-09-20