AI keeps getting more powerful, making it harder to judge how smart models actually are

AI keeps getting more powerful, making it harder to judge how smart models actually are

How do you judge an AI model when it’s already starting to perform better than human beings? That’s the challenge faced by researchers like Russell Wald, executive director of the Stanford Institute for Human-Centered Artificial Intelligence (HAI).  “As of 2024, there are very few task categories where human ability surpasses AI, and even in these areas, the performance gap between AI and humans is shrinking rapidly,” Wald said last week in a pr…