• N0body@lemmy.dbzer0.com
    link
    fedilink
    English
    arrow-up
    57
    arrow-down
    1
    ·
    5 days ago

    The tested LLMs fared much worse, though, when the Apple researchers modified the GSM-Symbolic benchmark by adding “seemingly relevant but ultimately inconsequential statements” to the questions

    Good thing they’re being trained on random posts and comments on the internet, which are known for being succinct and accurate.