Raschka's mega visual guide to text classification LLMs, from bag-of-words to Jev
rasbt · x · 2026-09-29
Sebastian Raschka published a long-form article tracing language models for text classification, from bag-of-words through RNNs, CNNs, and transformers to calibration, with hands-on experiments on accuracy and efficiency.
- On Jev: His view shifted from "classifiers used to be my bread & butter; I can build this myself" to "this actually works better than I thought." SOTA LLMs can do the same tasks, but Jev is faster and cheaper; versus task-specific classifiers, its edge is generality.
- Thesis: Jev is essentially a text classifier — but not "just" one. The piece offers an educated guess at its methodology and explains why it became a phenomenon in technical circles.
More from Models
- OpenRouter coding model share: GLM 5.3 Flash leads at 29.2%, DeepSeek V4.1 Flash at 25.6% — togethercompute · 2026-09-29
- Why classification models are making a comeback: pre-training quality, per new Jev analysis — rseroter · 2026-09-29
- ChatGPT flags database diagram prompt as erotic content, Turso cofounder shares — glcst · 2026-09-29
- PostHog's Jeeves: a 9B decision model scoring 0.935 on JevBench — petrusenko_max · 2026-09-29
- NVIDIA open-sources Kumo Tabular foundation models for tabular data with permissive license — jure · 2026-09-29
- Grok leak roundup: Bel previewed, ~700 token/s speeds, new 'aeon' codename — cedric_chee · 2026-09-29