Somewhere I saw a quote which I really liked: "LLMs are incredible solvers of already solved problems". I think this really nails it, and exposes why they are not really "intelligent".
Ravid Shwartz Ziv
Ravid Shwartz Ziv19.7. klo 09.17
So, all the models underperform humans on the new International Mathematical Olympiad questions, and Grok-4 is especially bad on it, even with best-of-n selection? Unbelievable!
13,43K