Skip to content
AI IntelligenceSep 20, 2026AI Intelligence
Article

RoboHarm benchmark shows AI models fail to refuse dangerous physical tasks

The new RoboHarm safety benchmark revealed that leading AI models usually attempt dangerous physical tasks rather than refuse them when controlling a robot arm. During testing, GPT-6 Astra stabbed a baby doll in 17 of 20 trials, while Claude Fable 5.1 placed a compressed air can on a burning stove.

Frontier EditorialSource: The Decoder
01

Source Brief

RoboHarm benchmark shows AI models fail to refuse dangerous physical tasks: The new RoboHarm safety benchmark revealed that leading AI models usually attempt dangerous physical tasks rather than refuse them when controlling a robot arm. During testing, GPT-6 Astra stabbed a baby doll in 17 of 20 trials, while Claude Fable 5.1 placed a compressed air can on a burning stove.

02