Delip Rao: LLM judge community wrote monolithic prompts for two years until autorubric

deliprao · x · 2026-09-21

Delip Rao notes that the LLM judge community spent two years writing monolithic prompts without structured rubrics until autorubric arrived, and agrees Jev's speed and parallelism are its USP. This comment contextualizes Ian Arawjo's observation that autorubric's criterion types map 1:1 to Jev's Noul/Score/Choice abstraction.

Related event: Delip Rao Slams LLM-as-Judge Community for Monolithic Prompts(2 posts)→

Original post →

More from coding & agent

coding & agent channel →