Comment by AI Security Institute (AISI)

As AI agents are given more autonomy and harder tasks, underestimating their capabilities becomes more consequential.

By open-sourcing not only Inspect, but also our methods and infrastructure where we can, we hope to help researchers, organisations, and other evaluators stand up rigorous evaluation capability without starting from zero.

It is clear from our experience that to run high quality evaluations that elicit high fidelity information to the potential risks posed by frontier systems, it is important for independent evaluators to have: Access to a Helpful Only (HO) version of ...