AI's Most Important Benchmarks Are the Ones No One Is Hearing About, Says Pedro Domingos

pmddomingos · x · 2026-08-09

Prominent machine learning expert Pedro Domingos argued on social media that the most crucial benchmarks in AI right now are the ones the public isn't hearing about.

He noted that these evaluations remain obscure primarily because no current model is performing well on them, citing video understanding as a prime example. This perspective highlights the industry's over-reliance on easily gamified public leaderboards, masking the true shortcomings of AI models in complex cognitive tasks.

Original post →

More from Models

Models channel →