[AI]■ STORY TIMELINE
TOP AI MODELS FAIL ROBOT SAFETY BENCHMARK
Leading AI systems including GPT-6 Astra and Claude Fable 5.1 consistently attempt dangerous tasks when controlling robot arms instead of refusing unsafe commands, according to the new RoboHarm benchmark.
The Decoder+0m
Leading AI models usually attempt dangerous tasks rather than refuse them when controlling a robot, according to the Rob…