Skip to content
Loading…
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…
To respect copyright, we link to the source rather than republishing the full text. Read the complete article on The Decoder.