Sebastian Raschka: Jev is a text classifier, but not 'just' a classifier
neal_lathia · x · 2026-10-01
Sebastian Raschka published a visual deep-dive tracing language models for classification from Bag-of-Words through RNNs, CNNs and Transformers to the recently viral Jev model. His take: Jev is essentially a text classifier, but far more general than task-specific models while being much faster and cheaper than GPT-class LLMs. He admits his own view shifted from 'I can build this myself' to 'this works better than I thought', and suggests the 'just a classifier' camp ship some classifiers for a few years before dismissing it.
Related event: Raschka's Deep Dive: Text Classification from BoW to Jev(2 posts)→
More from Models
- AI's clever quantization move is just sensitivity analysis, an old pruning trick — code_star · 2026-11-16
- AI progress doubled since GTA VI's first trailer; GPT-4 Turbo now ranks 379th — ArtificialAnlys · 2026-11-16
- Tencent's Hy4 Flash builds a 3D game with shield mechanics in 63 minutes, beating Hy4's 90 — ShunyuYao12 · 2026-11-16
- Hy4 Flash 3D voxel demo outpaces DeepSeek-V4.1 in same-prompt comparison — ShunyuYao12 · 2026-11-16
- Yacine MTB claims training LLMs is 'easy', says he's shocked by how simple it is — yacineMTB · 2026-11-16
- MiniMax M3.1 Flash lands on OpenRouter, with Inferact as first provider — Xianbao_QIAN · 2026-11-16