irelephant [he/him]@programming.devM to iiiiiiitttttttttttt@programming.devEnglish · 3 months agoWe put the Thing That Can't Do Numbers™ in your spreadsheetsprogramming.devexternal-linkmessage-square104fedilinkarrow-up1894arrow-down18
arrow-up1886arrow-down1external-linkWe put the Thing That Can't Do Numbers™ in your spreadsheetsprogramming.devirelephant [he/him]@programming.devM to iiiiiiitttttttttttt@programming.devEnglish · 3 months agomessage-square104fedilink
minus-squareThe Ramen Dutchman@ttrpg.networklinkfedilinkEnglisharrow-up1·edit-23 months ago It’s less accurate and doesn’t risk hallucinating I might be mistaken, but don’t these two lines mean the exact opposite in this context? Is AI more often right, or more often wrong?
minus-squareT156@lemmy.worldlinkfedilinkEnglisharrow-up1·3 months agoBoth, because the way it’s right and wrong are different. Sentiment analysis might misclassify some of the data, but it doesn’t risk making things up wholescale like an LLM would.
I might be mistaken, but don’t these two lines mean the exact opposite in this context?
Is AI more often right, or more often wrong?
Both, because the way it’s right and wrong are different.
Sentiment analysis might misclassify some of the data, but it doesn’t risk making things up wholescale like an LLM would.