Reasoning failures highlighted by Apple research on LLMs
appleinsider.com
A new paper from Apple's artificial intelligence scientists has found that engines based on large language models, such as those from Meta and OpenAI, still lack basic reasoning skills.

Their initial testing reveals that slight changes in the wording of queries can result in significantly different answers, undermining the reliability of the models.

  • JackGreenEarth@lemm.eeEnglish
    0·
    2 months ago

    Anyone who knows what LLMs are knew this from the start. They are good at creating text, but if you need the text to be true, they’re probably not the best tool for the job.

  • davel [he/him]@lemmy.mlEnglish
    0·
    2 months ago

    Such an unfortunate title. No one who knows what they’re talking about would say that LLMs can—or ever will—reason. It’s not a flaw when something can’t do what it wasn’t designed to do.