MotherDuck makes text classification 50x faster at ~1% of LLM cost
josh_wills · x · 2026-09-22
MotherDuck launched promptjev(), a SQL function powered by TypeSafe's new Jev model. Classifying 100k rows now takes 40 seconds and $0.50 at frontier-LLM accuracy, versus 32 minutes and $37 with an LLM — 50x faster at 1% of the cost. Engineers are calling it their favorite use case yet: intelligence cheap enough to apply to every row.
More from Infra
- Gas-for-AI-datacenters forum co-located with CoRL shows energy demand spillover — carlosdponx · 2026-11-12
- a16z podcast: Mike Volpi on Cisco's 70+ acquisition playbook and the AI buildout — a16z · 2026-11-12
- AMD to pass Intel in server revenue by mid-2027 as share gains 6 points a year — BenBajarin · 2026-11-12
- Study: Reflective Data Center Roofs Actually Cool Daytime Ground by 1.8-2.2°C — SumitGup · 2026-11-12
- Tsinghua's BaGuaLu-2 tames MoE expert-load spikes at runtime, accepted to SC26 — jiqizhixin · 2026-11-12
- antirez backs low-bit DeepSeek 4.1 Flash over Qwen 27B dense on Apple M5 Macs — antirez · 2026-11-12