Skip to content

"@motherduck ships prompt_jev() SQL powered by TypeSafe Jev: 100k-row text classification in 40s for $0.50 vs 32 min / $37 for an LLM."

Infrastructure

MotherDuck @motherduck

EN

  • 210.4k views
  • 515 likes
  • 511 bookmarks
  • 44 reposts
Poster from MotherDuck (@motherduck)

About this case

"Platform launch post: MotherDuck adds prompt_jev() for in-SQL text classification with Jev. Claims ~50× faster and ~1% cost versus an LLM on 100k rows (40s / $0.50 vs 32 min / $37) at frontier-LLM accuracy, with a blog link and chart image. Verified via fxtwitter."

Original posthttps://x.com/motherduck/status/2102077291081896307

Related cases