Laya and Jev: the return of the discriminative model, fast but narrow
maier_ak · x · 2026-09-28
A blog post examines the return of discriminative models via Laya: 0.950 on AG News at 7x speed, but only 0.425 on 77-label Banking77 vs 0.870 baseline, with its model card admitting zero-shot scores below the majority-class baseline.
More from Models
- ZooWork-ShopRanker: open 0.6B-8B e-commerce rerankers aligned to LLM-judged shopping preferences — _reachsumit · 2026-09-28
- Opus 5.5 reportedly an RL run on the Opus 5 pretrain, trained in ~2 months — haider1 · 2026-09-28
- Paper: 3 counting examples get gpt-3.5-turbo to 99% on strawberry, showing thinking is computational — ctjlewis · 2026-09-28
- AI Personal Assistants May Quietly Replace Much of Normal Human Interaction — GarrisonLovely · 2026-09-28
- Claude Opus 5 Shows Creative Tool-Regrasp Skills in Robot Manipulation Tasks — ericjang11 · 2026-09-28
- 421M-parameter open-source Laya returns answer probabilities in one pass at 40ms on a T4 — maier_ak · 2026-09-28