Jev hype gets pushback: embeddings plus logistic regression did this years ago
Loran750 · x · 2026-09-21
Pushback on the Jev hype wave: developer Loran750 notes everything the trending decision model Jev does was possible for years with frozen embeddings plus logistic regression — deterministic outputs, your own thresholds, no drifting API.
In his view Jev only wins in narrow cases: fast-changing categories where you want calibrated probabilities without a dataset. Otherwise it trades determinism for a lazier mode of delegating decisions to a black box.
Related event: Decision model Jev breaks adoption records amid hype and skepticism(14 posts)→
More from Models
- Tobi Lütke: local Dell server runs DeepSeek 4.1 Flash at ~300 tok/s, a billion tokens a month — BLUECOW009 · 2026-09-21
- LLMs still struggle at niche-domain labeling: a cluster-then-LLM pipeline with brittle second-pass labels — FanaHOVA · 2026-09-21
- A "decide" Primitive: Browser On-Device AI as a Native JS Control Flow — cocktailpeanut · 2026-09-21
- Rumor: GPT-6 Sol Lands Tuesday, Internal 'Bel' Deemed AGI; Opus 5.5 May Drop Monday — imjustnewatai · 2026-09-21
- Jev underperforms: researchers find better alternatives to GLiNER2-class extractors — airesearch12 · 2026-09-21
- Nym rebuilds its agent around Jev, a fast classifier model, for speed and cost gains — moyix · 2026-09-21