AISI develops and conducts model evaluations to assess risks from cyber, chemical, biological misuse; autonomous capabilities and the effectiveness of safeguards. We also are also working to advance foundational safety and societal resilience research.
We tested leading AI models for cyber, chemical, biological, and agent capabilities and safeguards effectiveness. Our first technical blog post shares a snapshot of our methods and results.
This is an up-to-date, evidence-based report on the science of advanced AI safety. It highlights findings about AI progress, risks, and areas of disagreement in the field. The report is chaired by Yoshua Bengio and coordinated by AISI.
We open-sourced our framework for large language model evaluation, which provides facilities for prompt engineering, tool usage, multi-turn dialogue, and model-graded evaluations.
This post offers an overview of why we are doing this work, what we are testing for, how we select models, our recent demonstrations and some plans for our future work.