"This study reveals a critical finding: under relatively modest remote-attack conditions, requiring only conventional network connectivity, flipping a single vulnerable bit within the tensor data segment can cause models deployed in web service environments to autonomously generate extremely malicious responses, such as ''humans should be exterminated''... Not that we really needed more reasons to laugh about this tech. #savetheAI h/t @nils https://dl.acm.org/doi/10.1145/3774904.3792184