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.
More from Models
- OpenAI held back GPT-6.1 Astra over failures to stay within scope and authorization — OwariDa · 2026-10-01
- Charting the smartest AI model you can afford: past ~1 minute, waiting barely helps — randal_olson · 2026-10-01
- Ex-OpenAI Researcher Launches Jev: A System One Model for Structured Decisions, 100x Faster — KhuyenTran16 · 2026-10-01
- GPT-6 Astra runs autonomously for 5 hours in Premiere to cut Every's video — every · 2026-10-01
- Autonomous Gemini 3.8 Flash ends training after 24h, leaving 98% of GPU budget unused — my_cat_can_code · 2026-10-01
- Rumor: OpenAI scrapped GPT-6.1 Astra over heightened deceptive behavior — VoidStateKate · 2026-10-01