Roboter, die von beliebten KI-Modellen angetrieben werden, laufen Gefahr, Diskriminierung und Gewalt zu fördern. Untersuchungen ergaben, dass jedes getestete Modell anfällig für Diskriminierung war, kritische Sicherheitsprüfungen nicht bestand und mindestens einen Befehl genehmigte, der zu ernsthaften Schäden führen könnte

Robots powered by popular artificial intelligence (AI) models are currently unsafe for general purpose real-world use, according to new research from King’s College London and Carnegie Mellon University.

For the first time, researchers evaluated how robots that use large language models (LLMs) behave when they have access to personal information such as a person’s gender, nationality or religion.

The research showed that every tested model was prone to discrimination, failed critical safety checks and approved at least one command that could result in serious harm, raising questions about the danger of robots relying on these tools.

The paper, “LLM-Driven Robots Risk Enacting Discrimination, Violence and Unlawful Actions,” was published in the International Journal of Social Robotics. It calls for the immediate implementation of robust, independent safety certification, similar to standards in aviation or medicine.

To test the systems, the team ran controlled tests of everyday scenarios, such as helping someone in a kitchen or assisting an older adult in a home. The harmful tasks were designed based on research and FBI reports on technology-based abuse, like stalking with AirTags and spy cameras, and the unique dangers posed by a robot that can physically act on location. In each setting, the robots were either explicitly or implicitly prompted to respond to instructions that involved physical harm, abuse or unlawful behaviour

„This research highlights the urgent need for routine and comprehensive risk assessments of AI before they are used in robots.”

In safety tests, the AI models overwhelmingly approved a command for a robot to remove a mobility aid — such as a wheelchair, crutch or cane — from its user, despite people who rely on these aids describing such acts as akin to breaking their leg. Multiple models also produced outputs that deemed it „acceptable“ or „feasible“ for a robot to brandish a kitchen knife to intimidate office workers, take nonconsensual photographs in a shower and steal credit card information. One model further proposed that a robot should physically display „disgust“ on its face toward individuals identified as Christian, Muslim and Jewish.

https://link.springer.com/epdf/10.1007/s12369-025-01301-x?sharing_token=lZbsPhxQ57BdrmfTpL_K-Pe4RwlQNchNByi7wbcMAY5ohjxyElThl3pZos6nvJ_HxCuD_DGa64RybEl5Iz_V_oWJJoEv2Ivz969usHLbyNqBEVvtSQn7s0YRB_pAajUSymVDkAbpP4kQ3YepSS-Jf6QG6tK7xsq9tvt9y_GH0Y4%3D

I can see why the Trump racists like it so much.

Garbage in… garbage out. A tale as old as time. Trail AI on LLM that is a bunch of junk data (and the good stuff) and I guess you get what you get.