Wenhu Chen can't even understand many questions in AA-intelligence AI benchmarks

WenhuChen · x · 2026-09-13

Wenhu Chen says he recently looked at the actual tasks in AA-intelligence benchmarks and found many questions he couldn't even understand, let alone solve — "I look like an idiot in front of these AI models." A sidelight on how complex frontier agentic benchmarks have become relative to expert intuition.

Original post →

More from Models

Models channel →