ArcticDagger@feddit.dk to Science@mander.xyz · 1 年前LLMs produce racist output when prompted in African American Englishwww.nature.comexternal-linkmessage-square35fedilinkarrow-up192arrow-down117
arrow-up175arrow-down1external-linkLLMs produce racist output when prompted in African American Englishwww.nature.comArcticDagger@feddit.dk to Science@mander.xyz · 1 年前message-square35fedilink
minus-squareHamartiogonic@sopuli.xyzlinkfedilinkarrow-up2·1 年前An LLM needs to evaluate and modify the preliminary output before actually sending it. In the context of a human mind that’s called thinking before opening your mouth.
minus-squareBrave Little Hitachi Wand@lemmy.worldlinkfedilinkEnglisharrow-up4·1 年前Who among us couldn’t benefit from a little more of that?
minus-squareHamartiogonic@sopuli.xyzlinkfedilinkarrow-up1·11 个月前Humans aren’t always very good at that, and LLMs were trained on stuff written by humans, so here we are.
minus-squareBrave Little Hitachi Wand@lemmy.worldlinkfedilinkEnglisharrow-up2·11 个月前Exciting new product from the tech industry: Fruit from the poisoned tree!
An LLM needs to evaluate and modify the preliminary output before actually sending it. In the context of a human mind that’s called thinking before opening your mouth.
Who among us couldn’t benefit from a little more of that?
Humans aren’t always very good at that, and LLMs were trained on stuff written by humans, so here we are.
Exciting new product from the tech industry: Fruit from the poisoned tree!