Humanising LLM Outputs Is Dumb

> 让 LLM 输出更具"人性"很蠢

HN 228 分 · 175 条评论 · 作者 kuberwastaken · 来源 kuber.studio · HN 讨论

> HN 228 分 · 175 条评论 · 作者 kuberwastaken · 来源 kuber.studio · HN 讨论

热门评论

1. @Xcelerate You ever read a work of literature with such flowery language that right after you've read a paragraph, you pause and realize you have no clue what you actually read, only to read the paragraph maybe a second or third time and have your mind space out again and again on each successive attempt?

⋯ 继续阅读请开通会员 ⋯