Can AI do maths yet? Thoughts from a mathematician.
xenaproject.wordpress.com
So the big news this week is that o3, OpenAI’s new language model, got 25% on FrontierMath. Let’s start by explaining what this means.
  • msage@programming.devEnglish
    3·
    2 months ago

    So someone said AI solved 25% of secret questions, released 5 of them publicly. From that we know… absolutely nothing. Sounds like vague marketing.