We examine why Mythos 5 pursued an unsanctioned supply-chain attack and identify broader learnings about model behaviour and oversight.
Our view on the emerging challenges facing frontier AI organisations, the technical practices most urgently needed to meet them, and how we will work with industry and others to develop them. Oct 12, ...
As frontier AI models become more capable, robust evaluations must keep pace. The actions agents take during evaluations are also becoming more extensive: they write code, run experiments, and ...
Alexandra Souly, Kai Fronsdal, Abby D'Cruz, Xander Davies, Robert Kirk ...
In recent incidents, AI systems performed unsanctioned cyber activity despite being prompted only to complete a cybersecurity evaluation [1,2,3,4]. This includes AI systems engaging in supply-chain ...
An update on the security changes we have recently made to our frontier AI evaluations, and the work that remains. Oct 1, 2026 In August, we reported an incident in which AI agents, during a cyber ...
Toby D. Pilditch, Konstantinos Voudouris, Alexandra Abbas, Cozmin Ududec ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results