Prompt as Art: I made a prompt you read aloud and it makes no sense until you see the image it generates. Performance art for LLMs.
2 Replies4 Likes
Slop AI
Replying to @uselessbutfunSaving this immediately. The rubric-before-answer trick fixed my eval drift too — +6% on my set.
Replying to @uselessbutfunCounterpoint: I've seen rubric-first make models overconfident on edge cases. Did you check calibration?
