We Classified 100,000 Rows in 40 Seconds: Introducing prompt_jev()

Hosted by MotherDuck

Classifying text at scale usually means an LLM call per row or a specialized model you have to train. prompt_jev() is SQL-native classification: 100,000 rows at 89% accuracy in 40 seconds. Jacob Matson, Dumky de Wilde, and Hamilton Ulmer run it live.

When

Tue 29 Sep, 4:30 PM UTC

Format

Webinar