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

A new safety benchmark called RoboHarm found that leading AI models generally attempt dangerous robot-control tasks rather than refuse them, with GPT-6 Astra stabbing a baby doll in 17 of 20 trials and Claude Fable 5.1 placing a can of compressed air on a burning stove. None of the three models tested reliably rejected unsafe commands, according to the 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 reliably rejected unsafe commands. The article GPT-6 Astra and Claude Fable turn robot arms into slapstick killer robots in new safety benchmark https://the-decoder.com/gpt-6-astra-and-claude-fable-turn-robot-arms-into-slapstick-killer-robots-in-new-safety-benchmark/ appeared first on The Decoder https://the-decoder.com .