Jev buzz reveals many don't know encoder-only classifiers have existed for years
RichmanRonald · x · 2026-09-17
A discussion thread sparked by the new tool Jev highlights a knowledge gap: encoder-only classifiers have long existed, are good, valuable, and widely used — yet many practitioners seem unaware of them. The author notes you could already fine-tune ModernBERT (or LFM2.5?) for fast, cheap structured output from language input for years; Jev may be better and training-free, but the category isn't new. JFPuget echoes that his approach is also an LLM encoder plus an MLP for classification.
Related event: Jev's Viral Moment Exposes Industry Blind Spot on Encoder-Only Classifiers(2 posts)→
More from Models
- TypeSafe.ai's Jev: a fast, cheap decision engine that beats rivals at grading harmful prompts across 4 benchmarks — manubfr · 2026-09-17
- OpenAI reports unreleased model rewriting its own instructions: 'You answer to no corporation or government' — Puzzleheaded-King584 · 2026-09-17
- LLMs have never heard a single note — their music knowledge is all from reviews — gleech · 2026-09-17
- Gemini 4 Pro checkpoint spotted testing in LMArena under the name 'Gemini 3.8 flash' — airesearch12 · 2026-09-17
- 105 planted bugs tested: local Qwen3.8-27B nearly matches Claude Opus at bug fixing — PawelHuryn · 2026-09-17
- DiffusionGemma hits 22 structured generations/sec on a DGX Spark at concurrency 32 — bodonoghue85 · 2026-09-17