Hard Fork cover image

‘A.I.-Washing’ Layoffs? + Why L.L.M.s Can’t Write Well + Tokenmaxxing

Hard Fork

00:00

Bad rubrics produce bland prose

Jasmine Sun describes how human evaluators use crude writing rubrics, pushing models toward factual, sanitized, corporate-sounding text.

Play episode from 25:13
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app