‹ BackHN Continuity

Thread

How to win a beer with high-dimensional statistics

81 points · 11 comments · jamie-simon

  1. mdritch · · focus · HN ↗
    I recently did some analysis on how different style prompts like "be succinct" and "avoid mannered prose" affect LLM outputs and I also saw a ~circular relationship with a 2d dimensional reduction (MDS) of the similarity matrix. I wonder if it's some artifact of PCA/MDS + Gemma's output dist
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.