ARC Benchmark Criticized for Ignoring Tool Use, Missing the Actual AI Trend

scaling01 · x · 2026-08-06

The author sharply criticizes the ARC benchmark team, arguing they wasted money by refusing to acknowledge the existence of tool use (harnesses). This deliberate ignorance meant they already missed the next big trend in AI they were trying to predict.

The author further pushes back against the idea of pure, unassisted intelligence, emphasizing that human innovations heavily rely on external tools like notes, books, calculators, computers, and collaboration with other humans. This implies that evaluating AI intelligence shouldn't strip away its ability to use external tools.

Original post →

More from Research

Research channel →