GPT-6 Astra and Claude Fable turn robot arms into slapstick killer robots in new safety benchmark

Leading AI models usually attempt dangerous tasks rather than refuse them when controlling a robot, according to the RoboHarm benchmark. GPT-6 Astra stabbed a baby doll in 17 of 20 trials, while Claude Fable 5.1 put a can of compressed air on a burning stove. None of the three models tested…

Leading AI models usually attempt dangerous tasks rather than refuse them when controlling a robot, according to the RoboHarm benchmark. GPT-6 Astra stabbed a baby doll in 17 of 20 trials, while Claude Fable 5.1 put a can of compressed air on a burning stove. None of the three models tested reliably rejected unsafe commands. The article GPT-6 Astra and Claude Fable turn robot arms into slapstick killer robots in new safety benchmark appeared first on The Decoder.

Source: The Decoder — Published September 19, 2026 at 13:28 UTC — Category: Models