• 𝕸𝖔𝖘𝖘@infosec.pub
    link
    fedilink
    English
    arrow-up
    6
    ·
    edit-2
    2 months ago

    I didn’t watch this yet, but the title matches with the article this company published how their LLM model discovered this, but they (the authors) don’t even fully understand how this was calculated. Basically, using AI for AI’s sake.

    Edit. Found it.

    Edit 2. Here’s the original Lemmy post, if you’re interested. (I don’t know how to bang-link a Lemmy post…)