Oh-oh.

"The crux of our work is to demonstrate that advances in AI enable a standalone, self-replicating malware that is able to propagate across heterogeneous computer networks with no prior assumptions about host vulnerabilities, network topology, or system configurations. Existing works on cyber-offence predominantly use frontier models that excel at both logical reasoning and decision-making. The compute footprint of these models however precludes them from being integrated into a standalone malware, whose operation is independent from the availability of a model provider. We thus turn to smaller, open-weight models."