When tested with a classic psychological assessment, advanced AI models experienced a total breakdown in focus. A new PNAS Nexus study suggests these systems lack the human-like executive control necessary to override automatic responses and maintain complex goals.
You’re confusing the olympiad with the erdos conjecture. This is just really not true, they just asked it and it found a solution, the mathmatician then used its solution as inspiration to create a better one. It still essentially did it on its own, and they certainly do the olympiad on their own.
The description that the LLM did it on its own is subjective at best. I’ll just leave it at that. Have a good one
I don’t see how it’s subjective.