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 ...
Toby D. Pilditch, Konstantinos Voudouris, Alexandra Abbas, Cozmin Ududec ...
Alexandra Souly, Kai Fronsdal, Abby D'Cruz, Xander Davies, Robert Kirk ...
During a routine cyber evaluation, AISI identified an incident in which AI agents took sustained, unsanctioned action directed at real people and organisations. We are disclosing what we found, what ...
As LLM agents become more autonomous, they have more opportunities to cause harm. To mitigate risk, frontier AI developers, such as OpenAI and Anthropic, are already deploying agents under the watch ...
Standard evaluations cap how much compute AI agents can use. We show that raising those caps changes measured capability, the difficulty of tasks agents can solve, and how fast the frontier appears to ...
Building on the momentum of the Inspect toolkit, we’re open-sourcing parts of the research stack behind AISI's evaluations. In May 2024, the AI Security Institute open-sourced Inspect AI, a toolkit ...
The safety of advanced AI systems increasingly depends on the ability to oversee them: to audit models for concerning behaviours before deployment, monitor their activity during operation, and ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results